dagarre00dagarre00/claude-code-template/.claude/skills/gotcha-recording/SKILL.md

gotcha-recording

Skill1 starsChanged 29 days agoMITView on GitHub

Subagent-side (loaded on demand by developer) or conductor. How to capture a project-specific failure mode or footgun in docs/wiki/gotchas.md so future cycles avoid it. Trigger on "gotcha", "burned by", "footgun", "surprising behavior".

In this repository20 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- adversarial-reviewSkill
- clean-architectureSkill
- decision-recordingSkill
- design-system-checkSkill
- dispatch-handoffSkill
- feature-branchingSkill
- finding-dispositionSkill
- git-recoverySkill
- human-checkpointSkill
- plan-reviewSkill
- plan-writingSkill
- pr-createSkill
- simplicity-ladderSkill
- spec-writingSkill
- subagent-contractSkill
- subagent-dispatchSkill
- tdd-loopSkill
- update-toolkitSkill
- wiki-updateSkill

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Very specific:
Keep each field to one short paragraph in impersonal voice.
line 29

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

SKILL.md

Recording a Gotcha

Project-specific traps go in docs/wiki/gotchas.md (universal agent discipline belongs in .claude/rules/behavioral.md).

When

Record a gotcha when a surprising project/library/config quirk burned time, a passing test masked broken behavior, or two wiki pages contradicted each other in practice. Skip general language facts, typos, or already-documented rules.

Procedure

Append under the relevant section of docs/wiki/gotchas.md (## Critical for data corruption or security risks):

### <Short, scannable title>

**When:** <the exact situation that surfaces it>
**Symptom:** <what you saw>
**Cause:** <what was actually happening>
**Fix:** <what to do>
**Related:** [[entities/<slug>]], [[concepts/<pattern>]]

Keep each field to one short paragraph in impersonal voice. If no fix is known, write Fix: TBD and queue a wiki-todo.

Queue a docs/wiki/wiki-todos.md line if the gotcha implies a missing skill/command, or if gotchas.md reaches 20+ entries (**When:** count): - [ ] YYYY-MM-DD agent: gotchas.md has N entries — compact it during the next wiki health pass (use Follow-ups: if running as a subagent).
Ship with the change that discovered it (include docs/wiki/gotchas.md in the case's reported paths).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free