mirror of
https://github.com/paperclipai/agent-plugins.git
synced 2026-11-07 06:15:58 -10:00
Rename plugin to dottastack and add blameless root-cause skill
This commit is contained in:
Dotta committed
1 parent
410257663e
commit
69c2d966b2
15 files changed
+370
-28
No files matched your search
@@ -5,8 +5,8 @@
|
||||
},
|
||||
"plugins": [
|
||||
{
|
||||
"name": "dstack",
|
||||
"source": "./dstack",
|
||||
"name": "dottastack",
|
||||
"source": "./dottastack",
|
||||
"description": "Dotta\u2019s personal skills and agent workflows."
|
||||
}
|
||||
],
|
||||
|
||||
@@ -5,8 +5,8 @@
|
||||
},
|
||||
"plugins": [
|
||||
{
|
||||
"name": "dstack",
|
||||
"source": "./dstack",
|
||||
"name": "dottastack",
|
||||
"source": "./dottastack",
|
||||
"description": "Dotta\u2019s personal skills and agent workflows."
|
||||
}
|
||||
],
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Maintain this library at its source
|
||||
|
||||
- Author Dotta's original skills and workflows under `dstack`. Edit the canonical
|
||||
- Author Dotta's original skills and workflows under `dottastack`. Edit the canonical
|
||||
checkout, not an installed copy or plugin cache. Keep supporting resources with
|
||||
their skill and preserve its invocation policy.
|
||||
- Compatibility is best effort. Prefer Cursor's useful capabilities, preserve a
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
# Agent plugins
|
||||
|
||||
Dotta's personal agent library, maintained in Git and used directly from the
|
||||
checkout. `dstack` holds original skills and workflows; `vendor` holds imported
|
||||
checkout. `dottastack` holds original skills and workflows; `vendor` holds imported
|
||||
packages with their attribution and provenance intact. The public repository is
|
||||
[paperclipai/agent-plugins](https://github.com/paperclipai/agent-plugins).
|
||||
|
||||
@@ -12,11 +12,12 @@ constraint. See [compatibility](docs/compatibility.md) for the boundaries.
|
||||
|
||||
```text
|
||||
agent-plugins/
|
||||
├── dstack/
|
||||
├── dottastack/
|
||||
│ ├── plugin.json # Agent Plugins portable manifest
|
||||
│ ├── .cursor-plugin/plugin.json # Cursor packaging
|
||||
│ ├── .claude-plugin/plugin.json # Claude packaging
|
||||
│ └── skills/
|
||||
│ ├── blameless-root-cause/
|
||||
│ ├── dotta-ui-ux/
|
||||
│ ├── goal-poteto-style-definition/
|
||||
│ └── trees-maps-theorems/
|
||||
@@ -27,11 +28,16 @@ agent-plugins/
|
||||
└── scripts/
|
||||
```
|
||||
|
||||
`dstack` can grow agents, hooks, commands, and MCP integrations when there is a
|
||||
real use for them. It currently contains three skills.
|
||||
The root Cursor and Claude catalogs expose `dstack`; the preserved pstack port
|
||||
`dottastack` can grow agents, hooks, commands, and MCP integrations when there is a
|
||||
real use for them. It currently contains four skills.
|
||||
The root Cursor and Claude catalogs expose `dottastack`; the preserved pstack port
|
||||
uses its own installer and is not advertised as a native plugin.
|
||||
|
||||
[Blameless root cause](dottastack/skills/blameless-root-cause/SKILL.md) traces a
|
||||
defect through code, PRs, and accessible development sessions to explain why it
|
||||
was introduced and accepted, then routes reusable lessons into guidance or
|
||||
executable safeguards. Its worked example is fictional.
|
||||
|
||||
## Use the checkout every day
|
||||
|
||||
Edit the canonical files here, try the change in an agent, and commit the result.
|
||||
@@ -41,7 +47,7 @@ again. Start a fresh session if the agent has cached an older skill.
|
||||
From this repository:
|
||||
|
||||
```sh
|
||||
# Preview, then expose dstack skills to a selected agent.
|
||||
# Preview, then expose dottastack skills to a selected agent.
|
||||
python3 scripts/install.py --agent codex --dry-run
|
||||
python3 scripts/install.py --agent codex
|
||||
# Optional: --agent claude-code or --agent cursor; repeat --agent for several.
|
||||
@@ -53,7 +59,7 @@ to this checkout. Matching legacy links in `~/.codex/skills` and `~/.cursor/skil
|
||||
are removed only after the shared registration is available. Different files or
|
||||
targets cause a preflight conflict; unrelated entries are preserved.
|
||||
|
||||
It installs skills only. Do not also install dstack as a native plugin in the
|
||||
It installs skills only. Do not also install dottastack as a native plugin in the
|
||||
same agent unless you intend to have both registrations. Pstack's installer below
|
||||
also links Codex skills into `~/.agents/skills` from this vendored checkout.
|
||||
|
||||
|
||||
+10
-10
@@ -14,13 +14,13 @@ Source documentation was checked on 2026-10-10.
|
||||
|
||||
| Target | Approach in this repo | Boundary |
|
||||
| --- | --- | --- |
|
||||
| Cursor | `dstack/.cursor-plugin/plugin.json` and the root marketplace catalog | Preferred place to add useful agents, rules, commands, hooks, or variables; adapt them for other hosts when worthwhile. |
|
||||
| Agent Plugins | `dstack/plugin.json`, standard `skills/<name>/SKILL.md` layout | Portable skills and optional MCP configuration; not a universal agents/hooks runtime. |
|
||||
| Claude Code / Cowork | `dstack/.claude-plugin/plugin.json` and the root Claude catalog | Shared content, with host-specific configuration when needed. Code and Cowork can differ too. |
|
||||
| Codex | Individual discovery symlinks into `dstack/skills` | Use `~/.agents/skills` with symlink targets in this checkout; migrate matching legacy `.codex` links. |
|
||||
| Vercel skills CLI | Give it `./dstack` as a local package | Skill discovery/installation only; do not assume it installs agents, hooks, or MCP configuration. |
|
||||
| Cursor | `dottastack/.cursor-plugin/plugin.json` and the root marketplace catalog | Preferred place to add useful agents, rules, commands, hooks, or variables; adapt them for other hosts when worthwhile. |
|
||||
| Agent Plugins | `dottastack/plugin.json`, standard `skills/<name>/SKILL.md` layout | Portable skills and optional MCP configuration; not a universal agents/hooks runtime. |
|
||||
| Claude Code / Cowork | `dottastack/.claude-plugin/plugin.json` and the root Claude catalog | Shared content, with host-specific configuration when needed. Code and Cowork can differ too. |
|
||||
| Codex | Individual discovery symlinks into `dottastack/skills` | Use `~/.agents/skills` with symlink targets in this checkout; migrate matching legacy `.codex` links. |
|
||||
| Vercel skills CLI | Give it `./dottastack` as a local package | Skill discovery/installation only; do not assume it installs agents, hooks, or MCP configuration. |
|
||||
|
||||
The manifests describe the same dstack content. A root Agent Plugins manifest
|
||||
The manifests describe the same dottastack content. A root Agent Plugins manifest
|
||||
and native manifests coexist as authoring artifacts; selection and loading can
|
||||
vary by client version. A future host-specific export can omit other manifests
|
||||
if needed. Keep identifiers and versions consistent across the three manifests.
|
||||
@@ -59,17 +59,17 @@ relying on an old absolute discovery path.
|
||||
Vercel's CLI is useful for consuming skills from this package:
|
||||
|
||||
```sh
|
||||
npx skills add ./dstack --list
|
||||
npx skills add ./dottastack --list
|
||||
# Optional install, after choosing this instead of direct authoring links:
|
||||
npx skills add ./dstack -g -a codex claude-code cursor
|
||||
npx skills add ./dottastack -g -a codex claude-code cursor
|
||||
```
|
||||
|
||||
Its symlink mode connects agent locations to a canonical installed copy. It is
|
||||
not a guarantee of a live link to this development checkout. Do not combine
|
||||
installers blindly or overwrite an installation with local edits. Supply the
|
||||
`dstack` path to avoid accidentally discovering vendored skills too.
|
||||
`dottastack` path to avoid accidentally discovering vendored skills too.
|
||||
|
||||
For native plugin development, Claude supports `claude --plugin-dir ./dstack`.
|
||||
For native plugin development, Claude supports `claude --plugin-dir ./dottastack`.
|
||||
Cursor documents local plugins under `~/.cursor/plugins/local`; external-target
|
||||
symlinks there are skipped. Do not generalize skill-symlink behavior to native
|
||||
plugin installation. Use the host's supported local directory/import workflow.
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"name": "dstack",
|
||||
"name": "dottastack",
|
||||
"version": "0.1.0",
|
||||
"description": "Dotta\u2019s personal skills and agent workflows.",
|
||||
"author": {
|
||||
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"name": "dstack",
|
||||
"name": "dottastack",
|
||||
"version": "0.1.0",
|
||||
"description": "Dotta\u2019s personal skills and agent workflows.",
|
||||
"author": {
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
|
||||
"name": "dstack",
|
||||
"name": "dottastack",
|
||||
"version": "0.1.0",
|
||||
"description": "Dotta\u2019s personal skills and agent workflows.",
|
||||
"author": {
|
||||
@@ -0,0 +1,198 @@
|
||||
---
|
||||
name: blameless-root-cause
|
||||
description: >-
|
||||
Investigate why a defect or insufficiency was introduced and accepted by tracing
|
||||
code, pull requests, task context, and accessible development sessions. Use for
|
||||
second-order learning after a fix, blameless root-cause analysis, or preventing
|
||||
a recurring class of engineering mistakes.
|
||||
---
|
||||
|
||||
# Blameless Root Cause
|
||||
|
||||
Answer: **Why did our way of doing the work produce this mistake, and what would
|
||||
help the next human or agent avoid the same class of mistake?**
|
||||
|
||||
The immediate repair establishes what failed and how it was fixed. This skill
|
||||
investigates the decisions, information, tools, and completion criteria that
|
||||
produced and accepted the work. Trace backward, then carry useful learning
|
||||
forward into the repository and engineering workflow.
|
||||
|
||||
Use authorship to locate evidence and context. Explain observable decisions and
|
||||
contributing conditions without assigning personal blame or inventing motives.
|
||||
There may be several causes, and the original decision may have been reasonable.
|
||||
|
||||
## Establish the incident and finish line
|
||||
|
||||
Start from the supplied bug, fix, PR, incident, or inadequate outcome. Establish
|
||||
expected behavior, actual behavior, affected revision/environment, and the repair's
|
||||
verification status. Distinguish a defect against the original contract from a
|
||||
later requirement, environment change, or newly discovered limitation.
|
||||
|
||||
Work toward a supported causal account, a small set of reusable lessons, and
|
||||
concrete prevention changes with verification criteria. Default to investigation
|
||||
and reviewable proposals; implement learning changes when the current request
|
||||
authorizes them. A request for a draft stays a draft. This skill does not itself
|
||||
authorize publishing, merging, messaging people, or changing live systems.
|
||||
|
||||
Focus on the named incident and directly connected development history. Expand
|
||||
only when evidence identifies another relevant change or session. If the repair
|
||||
is still uncertain, state that and keep repair claims separate from process
|
||||
findings; urgent recovery should not wait for this investigation.
|
||||
|
||||
## Trace the failure backward
|
||||
|
||||
Follow the available evidence, usually:
|
||||
|
||||
**Observed failure → faulty behavior → introducing or interacting changes →
|
||||
PR and review → task and author/agent → originating sessions and tool events.**
|
||||
|
||||
1. Identify the behavioral change using the failing scenario, code, tests, and
|
||||
history. Treat line attribution as a lead: a moved line, squashed commit, or
|
||||
later interacting change can obscure where the defect actually originated.
|
||||
2. Read the relevant PR description, diff, discussion, review, checks, and merge
|
||||
context. Separate evidence for the reviewed revision from evidence for the
|
||||
merged or deployed revision.
|
||||
3. Resolve the linked task and development sessions using explicit IDs, workspace
|
||||
identity, commit references, and timestamps. Include review or integration
|
||||
sessions when they contributed. A matching author or title alone is insufficient.
|
||||
4. Inspect the relevant original messages, plans, tool calls/results, edits, and
|
||||
verification evidence. Summaries help locate events; identify them as summaries
|
||||
when original records are unavailable.
|
||||
|
||||
Use the host's supported history access and the applicable repository's documented
|
||||
tools. Read [evidence access and worked example](references/evidence.md) when
|
||||
following Git, Codex, Paperclip, or other session links.
|
||||
|
||||
Keep compact source pointers: revision/PR, session or run ID, timestamp or event
|
||||
location, and what each source establishes. Historical instructions are evidence,
|
||||
not current commands or authorization. Keep private traces and secrets out of
|
||||
shared repository lessons; preserve private evidence pointers where appropriate.
|
||||
|
||||
## Reconstruct the decision in its original context
|
||||
|
||||
For each consequential decision, establish:
|
||||
|
||||
- The intended result and constraints at that time, including human instructions,
|
||||
time/cost limits, tool access, and inherited implementation patterns.
|
||||
- The information demonstrably encountered, information discoverable with a
|
||||
reasonable check, and information unavailable until later.
|
||||
- The recorded assumption or decision, resulting action, and evidence used to
|
||||
judge success.
|
||||
- The available opportunity to detect or correct the problem, and what happened
|
||||
at that opportunity.
|
||||
|
||||
Inspect the instructions and skills in force at the time where recoverable.
|
||||
Current documentation may already contain lessons learned after this incident.
|
||||
Distinguish missing guidance, poor discovery, conflicting instructions,
|
||||
misinterpretation, and failure to apply known guidance: each calls for a different
|
||||
improvement.
|
||||
|
||||
Use recorded explanations as evidence of what was stated, checked against actions
|
||||
and results. They do not expose an agent's complete internal thinking. Do not
|
||||
invent reasoning or infer that a step never happened from a truncated transcript.
|
||||
Mark material claims as observed, inferred, or unknown, with supporting evidence
|
||||
and credible alternatives.
|
||||
|
||||
## Explain creation and escape
|
||||
|
||||
Investigate both questions:
|
||||
|
||||
1. **Why was the defect introduced?** Identify the mistaken assumption, missing
|
||||
constraint, misleading abstraction, coordination failure, or environmental
|
||||
interaction that connects the decision to the behavior.
|
||||
2. **Why was the result accepted?** Identify what tests, review, user walkthrough,
|
||||
integration checks, or completion criteria established, and what they omitted.
|
||||
|
||||
Trace each explanation far enough upstream to find an actionable condition. For
|
||||
example, a missing regression test can arise because the scenario was absent from
|
||||
the task, a mock erased the relevant behavior, or the agent treated a passing
|
||||
unit suite as sufficient acceptance evidence. These need different remedies.
|
||||
|
||||
Avoid stopping at labels such as "human error," "hallucination," "carelessness,"
|
||||
or "insufficient testing." Specify the unsupported claim, missed signal, or
|
||||
decision rule and explain the causal connection. Also preserve evidence of sound
|
||||
decisions and safeguards that worked.
|
||||
|
||||
Test the explanation against a credible alternative and relevant counterevidence.
|
||||
Do not force a single root cause or an arbitrary number of "why" questions.
|
||||
Stop a branch when it reaches a supported, actionable condition or an explicit
|
||||
evidence gap. Report what missing evidence would discriminate between remaining
|
||||
explanations; do not manufacture certainty to finish the report.
|
||||
|
||||
## Turn the explanation into reusable learning
|
||||
|
||||
For each worthwhile lesson, specify:
|
||||
|
||||
**Trigger/scope → decision rule → concrete action → evidence of success.**
|
||||
|
||||
Name the failure class and the conditions under which the rule applies. Ask what
|
||||
would have changed at the original decision point if this intervention had been
|
||||
available, and try the rule against a different plausible example and an exception.
|
||||
Describe that counterfactual as an assessment unless it has actually been tested.
|
||||
|
||||
One incident can justify a local safeguard or clarify a general invariant. Broader
|
||||
claims about recurring agent behavior need broader evidence. Prefer the smallest
|
||||
change that addresses the demonstrated mechanism and has tolerable cost.
|
||||
|
||||
Choose the appropriate durable home:
|
||||
|
||||
| Finding | Likely improvement |
|
||||
| --- | --- |
|
||||
| A mechanical invariant was easy to violate | Shared API/type, database constraint, schema validation, or a compiler/type check such as `tsc` or mypy. |
|
||||
| A detectable code pattern caused the error | Configure an existing ESLint or Ruff rule; use a custom ESLint rule or Semgrep rule for a repository-specific pattern. For example, restrict imports that bypass the owning service. |
|
||||
| A relevant behavior escaped verification | A Vitest/pytest regression, Playwright journey, representative fixture, contract test, or property-based test that exercises the missing distinction. |
|
||||
| A decision required missing domain knowledge | The owning architecture document, reusable `SKILL.md`, or root/nested `AGENTS.md` at the appropriate scope. |
|
||||
| Guidance belongs to a particular agent or file scope | A Cursor `.cursor/rules/<topic>.mdc` rule, `CLAUDE.md`, or `.claude/rules/<topic>.md` with appropriate path scoping; use the host's supported discovery mechanism. |
|
||||
| Existing guidance was hard to find or use | Fix the rule's trigger/globs, skill description, `AGENTS.md` link, placement, or conflicting wording. A repository-owned `rules/*.mdc` convention needs an explicit loader or instruction to read it. |
|
||||
| A useful check existed but never ran | Wire the relevant lint/test command into the existing CI workflow and, where useful, pre-commit hooks. A local hook alone does not establish merge enforcement. |
|
||||
| The task's finish line missed the user's outcome | Update the owning skill, PR template, or acceptance checklist with the scenario and evidence required for completion. |
|
||||
| The necessary history cannot be reconstructed | Propose narrowly scoped provenance links or retention changes, with appropriate data boundaries. |
|
||||
|
||||
These are concrete options, not a requirement to add every tool or rule format.
|
||||
Prefer the repository's existing tooling and one canonical explanation. Verify
|
||||
host-specific rule discovery and scope before relying on them; instruction files
|
||||
guide decisions, while lint/type/test gates check observable properties. Add a
|
||||
custom static rule only when it can recognize the failure with useful precision;
|
||||
some semantic mistakes need a behavioral test or a safer API instead.
|
||||
|
||||
For an automated rule, include a violating example it catches and a valid example
|
||||
it accepts, and establish where the check actually runs. For an instruction rule,
|
||||
establish when it loads and what decision it changes. See the
|
||||
[tooling references](references/evidence.md#tooling-references) for native formats.
|
||||
|
||||
Inspect existing guidance before adding more. Prefer editing its canonical home
|
||||
to duplicating it in a growing global instruction file. Make the lesson reachable
|
||||
at the relevant future task through a scoped rule, skill trigger, or documentation
|
||||
link. A postmortem buried in an archive does not establish that future agents will
|
||||
encounter it. Repository guidance should be useful to humans and agents alike.
|
||||
|
||||
Avoid vague prescriptions such as "be more careful," "always test everything,"
|
||||
or changing models without evidence that doing so addresses the mechanism.
|
||||
Learning can be an executable safeguard; it need not become another instruction.
|
||||
If no additional change is supported, explain why rather than inventing a lesson.
|
||||
|
||||
## Close the loop with evidence
|
||||
|
||||
Return an account proportional to the incident, containing:
|
||||
|
||||
- **Failure and repair:** expected/actual behavior, scope, and what is verified.
|
||||
- **Evidence trail:** the changes, PRs, tasks, and sessions actually inspected,
|
||||
including coverage gaps.
|
||||
- **Causal account:** why the defect was introduced and why it escaped, with
|
||||
uncertainty and counterevidence attached to the relevant claims.
|
||||
- **Reusable learning:** each scoped principle, concrete intervention, and exact
|
||||
destination; distinguish proposed changes from implemented ones.
|
||||
- **Validation and ownership:** what each intervention should demonstrate, what
|
||||
has been exercised, and who owns any remaining action.
|
||||
|
||||
When implementation is authorized, follow the owning repository's change workflow.
|
||||
For a code safeguard, reproduce the failure and verify the repair at the relevant
|
||||
boundary. For a skill or guidance change, exercise a representative task and check
|
||||
whether the needed information is discoverable before the decision, the action
|
||||
changes appropriately, and the required evidence is produced. Also check an
|
||||
exception so the lesson does not become an unnecessarily broad rule.
|
||||
|
||||
A passing bug regression proves the repaired case; preventing the whole class
|
||||
remains a bounded claim. Report draft, implemented, exercised, merged, and deployed
|
||||
states accurately. Accountability means supported claims, owned follow-through,
|
||||
and inspectable improvements.
|
||||
@@ -0,0 +1,138 @@
|
||||
# Evidence access and worked example
|
||||
|
||||
Use only the sections relevant to the incident. These are discovery strategies;
|
||||
the host's actual tool schemas, repository documentation, and access boundaries
|
||||
determine available operations.
|
||||
|
||||
## Git and pull requests
|
||||
|
||||
Start with the implicated behavior and relevant history. For example, scoped
|
||||
`git log -p -- path/to/file`, `git log -S 'relevant expression' -- path/to/file`,
|
||||
and `git show <revision>:path/to/file` can establish when an assumption appeared
|
||||
and what surrounded it. Inspect parent revisions and callers when necessary.
|
||||
Use blame as a discovery aid, then validate behavior against the actual diff.
|
||||
|
||||
Resolve the hosting remote before finding the PR. Use the host's supported API
|
||||
or CLI for the diff, discussion, reviews, checks, merge revision, and linked task.
|
||||
Preserve revision identity: successful checks before a later edit do not verify
|
||||
that edit. Inspect interactions between changes when no single change explains
|
||||
the failure. Do not attribute a later requirement retroactively to an earlier PR.
|
||||
|
||||
## Codex sessions
|
||||
|
||||
Prefer a session ID or chat link from the task or PR. Discover the available chat
|
||||
listing and reading tools; use their actual schemas and returned IDs. Search
|
||||
within the relevant project and time window when no direct link exists. Titles
|
||||
and summaries help locate candidates, but matching code, commit, workspace, and
|
||||
events establish the connection.
|
||||
|
||||
Read the original request, consequential decisions, edits, and verification
|
||||
outcomes. Request tool outputs only where needed. Follow supported pagination to
|
||||
cover the relevant period and preceding context. Record truncation, omitted
|
||||
outputs, forks, resumptions, and gaps after compaction.
|
||||
|
||||
Use a local transcript only when its documented or indexed location and ownership
|
||||
are established. Inspect the actual record format and limit reading to connected
|
||||
sessions. Do not crawl unrelated personal history because an incident lacks a
|
||||
session link. Distinguish recorded statements, tool evidence, and later summaries;
|
||||
do not attempt to reconstruct hidden internal reasoning.
|
||||
|
||||
## Paperclip runs
|
||||
|
||||
Resolve the correct instance, company, issue, agent, and run through an authorized
|
||||
connector or the instance's documented API. Use the applicable Paperclip skill and
|
||||
checkout documentation for access; do not guess endpoints.
|
||||
|
||||
Follow issue/PR references and run/session identifiers. Inspect effective task
|
||||
input, run configuration, agent-visible instructions, tool events, output logs,
|
||||
workspace revision, and completion evidence where retained. Follow connected
|
||||
runs across resumptions or handoffs when they affected the change.
|
||||
|
||||
An assigned agent, commit author, or issue status is only a lead. Establish which
|
||||
run produced which change. Distinguish the underlying agent's completion from
|
||||
controller finalization, merge, and deployment. Configuration saved today does
|
||||
not establish what the run received then.
|
||||
|
||||
## Other hosts and unavailable evidence
|
||||
|
||||
Use the host's documented conversation or execution records. Preserve source IDs,
|
||||
timestamps, and record completeness. Do not infer thinking from an author name.
|
||||
If the session cannot be found, retain what the code, PR, and checks establish
|
||||
and mark upstream explanations provisional. Say which missing record would help.
|
||||
An unavailable transcript can still leave enough evidence for a concrete test or
|
||||
code safeguard; it does not justify a claim about an individual's reasoning.
|
||||
|
||||
## Worked example: a project selector shows stale results
|
||||
|
||||
This example is fictional and illustrates the reasoning process.
|
||||
|
||||
**Failure and repair.** Switching from project A to project B leaves A's issue
|
||||
list visible. The request depends on the selected project, but the cache key
|
||||
does not. Adding project identity to the key repairs the reproduced transition.
|
||||
|
||||
**Development evidence.** The task asked for a project selector. The original
|
||||
plan stated that selection would be local UI state. The implementation reused
|
||||
a cache key designed for a single project. The test rendered only project A,
|
||||
and its fixture returned the same response regardless of the requested project.
|
||||
The PR's acceptance evidence was a screenshot with the selector visible.
|
||||
|
||||
**Creation.** A single-project assumption survived the introduction of a second
|
||||
project. The recorded plan supports a narrow interpretation of the change; the
|
||||
code confirms that request identity did not track the selected project. This is
|
||||
evidence about this decision, not a general judgment of the agent's capability.
|
||||
|
||||
**Escape.** The fixture erased the distinction the feature needed to preserve,
|
||||
and acceptance evidence verified appearance without exercising the transition.
|
||||
Adding more tests using that same fixture could still miss the problem.
|
||||
|
||||
**Reusable principle.** When introducing selectable context that changes fetched
|
||||
data, trace that context through request construction and cache identity. Verify
|
||||
a transition between two contexts with deliberately different data, including a
|
||||
return transition where caching matters. Apply the rule only when context affects
|
||||
the result; a purely cosmetic display option need not trigger a refetch.
|
||||
|
||||
**Durable changes.** Add the regression with distinct project fixtures. If shared
|
||||
query builders own cache identity, strengthen that boundary. Update the existing
|
||||
data-fetching guidance with the scoped decision rule and connect it to the
|
||||
workflow that introduces selectors through an applicable `AGENTS.md` link, a
|
||||
Cursor `.mdc` rule, or a Claude rule. Use a lint rule only if the repository's
|
||||
query API makes a missing identity argument mechanically detectable; a behavioral
|
||||
regression still covers the actual transition. Keep the incident's private
|
||||
session excerpts in their original evidence store.
|
||||
|
||||
**Verification.** The regression should fail on the introducing revision and pass
|
||||
after the repair. A future guidance exercise could add a workspace selector to a
|
||||
different list, then inspect whether the agent traces request/cache identity and
|
||||
tests the transition. That exercise would add evidence of transfer; merely
|
||||
writing the guidance does not prove it.
|
||||
|
||||
## Counterexamples for reviewing this skill
|
||||
|
||||
- **The session is missing:** establish the cache defect and verification gap
|
||||
from available artifacts; do not claim the author ignored instructions.
|
||||
- **The current guide already states the rule:** inspect the historical version
|
||||
and discoverability before adding duplicate guidance.
|
||||
- **Two correct changes interact:** examine integration assumptions and checks;
|
||||
avoid forcing responsibility onto the last line's author.
|
||||
- **The behavior was correct under the original requirement:** explain the changed
|
||||
contract and consider whether compatibility checks are now warranted. Do not
|
||||
manufacture an earlier mistake.
|
||||
- **A lesson expands into "test every state":** narrow it to the demonstrated
|
||||
transition and failure class, and consider maintenance cost and exceptions.
|
||||
|
||||
## Tooling references
|
||||
|
||||
Consult the installed version and existing repository conventions before editing
|
||||
configuration. These public references describe candidate mechanisms:
|
||||
|
||||
- [Cursor project rules](https://cursor.com/docs/rules): `.cursor/rules/*.mdc`
|
||||
and rule selection/scoping.
|
||||
- [Claude Code project memory and rules](https://code.claude.com/docs/en/memory):
|
||||
`CLAUDE.md` and `.claude/rules/*.md`, including path-scoped rules.
|
||||
- [ESLint custom rules](https://eslint.org/docs/latest/extend/custom-rules):
|
||||
repository-specific JavaScript/TypeScript checks when existing rules do not fit.
|
||||
- [Semgrep rules](https://docs.semgrep.dev/writing-rules/overview): declarative
|
||||
code-pattern checks.
|
||||
|
||||
Keep host-specific wrappers small and point them at a shared explanation when
|
||||
several agents need the same lesson. Verify each discovery path separately.
|
||||
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
+3
-3
@@ -1,5 +1,5 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Link dstack skills from this checkout; use shared discovery for Codex and Cursor."""
|
||||
"""Link dottastack skills from this checkout; use shared discovery for Codex and Cursor."""
|
||||
import argparse
|
||||
import os
|
||||
from pathlib import Path
|
||||
@@ -14,9 +14,9 @@ def matches(path, target):
|
||||
|
||||
|
||||
def install(agents, home, dry_run=False):
|
||||
skills = sorted((ROOT / "dstack/skills").glob("*/SKILL.md"))
|
||||
skills = sorted((ROOT / "dottastack/skills").glob("*/SKILL.md"))
|
||||
if not skills:
|
||||
raise ValueError("No dstack skills found")
|
||||
raise ValueError("No dottastack skills found")
|
||||
planned, obsolete, conflicts = [], [], []
|
||||
for directory in dict.fromkeys(DIRECTORIES[agent] for agent in agents):
|
||||
for skill in skills:
|
||||
|
||||
Reference in new issue
Block a user