when-to-use-and-avoid
Skill0 starsChanged 15 days agoMITView on GitHub
State both conditions so an agent can decline a skill that does not fit the target. Use when a skill is broad enough to be tempting in situations where it is wrong
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
- signal-and-pitfall-sectionsSkill
- 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
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
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 20
Write the use-when clause as an observable condition, not a topic
- Distinctive: line 21
Write the avoid-when clause as the situation where it misleads
- Distinctive: line 22
Check the clauses do not overlap
- Distinctive: line 24
Add a signal that reveals the avoid-when condition early
≈ “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
When to Use and Avoid
State both conditions so an agent can decline a skill that does not fit the target
Use when: a skill is broad enough to be tempting in situations where it is wrong
Avoid when: the skill is a narrow mechanical step with no plausible misapplication
Procedure
- Write the use-when clause as an observable condition, not a topic
- Write the avoid-when clause as the situation where it misleads
- Check the clauses do not overlap
- Make both clauses specific enough to be checked against a target
- Add a signal that reveals the avoid-when condition early
- Re-read after a failed engagement and refine from the failure
Signals
- the use-when clause names something observable in a capture or request
- the avoid-when clause names a concrete exclusion
- the two clauses cannot both be true
- an early signal warns when the avoid condition holds
Patterns
1. Observable use
a cacheable response reflects a query value2. Concrete avoid
response carries no-store on every request3. Early warning
age header is zero on repeats, so nothing is cachedPitfalls
- Writing 'use when testing caching', which is a topic and not a condition
- Omitting avoid-when so the skill is applied everywhere
- Making the clauses so broad they are always true
Done when
- both clauses are observable and mutually exclusive
- at least one signal reveals the avoid condition early
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.

