signal-and-pitfall-sections
Skill0 starsChanged 15 days agoMITView on GitHub
Write signals as observations and pitfalls as the mistakes that produce false findings. Use when a skill needs to help a reader decide mid-procedure whether they are on track
In this repository49 other files it gives its agents.
- argument-construction-from-artifactsSkill
- audit-log-of-tool-callsSkill
- bounded-output-designSkill
- capability-negotiation-checkSkill
- changelog-and-versioningSkill
- concurrency-and-ordering-checkSkill
- context-window-managementSkill
- credential-isolationSkill
- data-retention-policySkill
- description-as-contractSkill
- destructive-action-confirmationSkill
- destructive-tool-gatingSkill
- deterministic-command-choicesSkill
- done-when-criteriaSkill
- error-shape-for-agentsSkill
- fixture-driven-transcript-testsSkill
- human-in-the-loop-escalationSkill
- idempotency-annotationSkill
- input-schema-strictnessSkill
- least-privilege-tool-grantsSkill
- lifecycle-test-initialize-then-toolsSkill
- local-vs-remote-boundarySkill
- one-procedure-per-skillSkill
- pagination-and-limit-disciplineSkill
- parallel-tool-call-safetySkill
- protocol-conformance-testSkill
- protocol-version-handshakeSkill
- publishing-a-pack-locallySkill
- rate-limit-respectSkill
- reference-canonicalisationSkill
- replay-transcript-for-regressionSkill
- restart-and-reload-semanticsSkill
- scope-guard-before-executionSkill
- search-then-fetch-patternSkill
- secrets-via-environmentSkill
- server-discovery-and-trustSkill
- skill-frontmatter-contractSkill
- stdio-client-configSkill
- stdout-purity-checkSkill
- third-party-server-sandboxingSkill
- tool-call-budgetingSkill
- tool-call-error-pathsSkill
- tool-error-without-retry-stormSkill
- tools-list-schema-validationSkill
- tool-surface-minimisationSkill
- tool-verb-namingSkill
- transport-choiceSkill
- verify-tool-output-before-reportingSkill
- when-to-use-and-avoidSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 24
Remove any signal that is really an interpretation
- Distinctive: line 25
Check the pitfalls against your own past notes
- Distinctive: line 31
no signal restates a step
- Distinctive: line 62
every signal is verifiable from captured evidence
- Distinctive: line 63
every pitfall names an action and the false finding it causes
≈ “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.
Files
Signal and Pitfall Sections
Write signals as observations and pitfalls as the mistakes that produce false findings
Use when: a skill needs to help a reader decide mid-procedure whether they are on track
Avoid when: the procedure is entirely deterministic and has no judgement step
Procedure
- List the observations that confirm the skill is working
- Phrase each as something visible in a response, header or byte count
- List the mistakes that have produced false positives for this technique
- Phrase each pitfall as a specific action to avoid
- Remove any signal that is really an interpretation
- Check the pitfalls against your own past notes
Signals
- each signal can be verified from a capture
- each pitfall names a concrete wrong action
- no signal restates a step
- the pitfalls explain a class of false positive
Patterns
1. Observable signal
age header resets to zero when the header changes2. Actionable pitfall
replaying a POST that creates a record each time3. Removed signal
looks suspicious: too vague to verifyPitfalls
- Writing signals that are conclusions rather than observations
- Listing pitfalls that are just restatements of the steps
- Omitting the false-positive class that this technique invites
Done when
- every signal is verifiable from captured evidence
- every pitfall names an action and the false finding it causes
References
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
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.

