ask-me
Skill15 starsChanged 15 days agoApache-2.0View on GitHub
Constructively interview someone about an idea, task, project or decision so useful work can start. Use when explicitly asked to be interviewed, including “ask me”; ordinary task requests do not start this interview.
15 other projects use a version of this.
Adopted by
Most recently taken up by
- catesandrew/skillstheir own version, first seen Nov 1, 2026
- TanKaizokuO/claude-skillstheir own version, first seen Oct 20, 2026
- grinbuddy/claude-skillstheir own version, first seen Oct 17, 2026
- master-g/skillstheir own version, first seen Oct 13, 2026
- nhhthong/skillstheir own version, first seen Oct 13, 2026
- himadajin/skillstheir own version, first seen Oct 11, 2026
Other versions15 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 15
- ivklgn/ai-kit★ 12same name
- ivklgn/bag-of-skills★ 12same name
- cassianodiniz/cass★ 4same name
- cassianodiniz/Titan★ 4same name
- Chrisamansood/chris-ai-productivity★ 2same name
- catesandrew/skills★ 1same name
- DanaResearchGroup/agent-skills★ 1same name
- himadajin/skills★ 1same name
- madanlalit/agentskills★ 1same name
- nhhthong/skills★ 1same name
5 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository95 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- llms.txtllms.txt
- agent-mailboxSkill
- agent-outputSkill
- ask-gateSkill
- audit-coupled-constantSkill
- budget-checkSkill
- build-prototypeSkill
- caller-optionsSkill
- cold-reviewSkill
- debug-taskSkill
- define-termsSkill
- defuddleSkill
- design-an-interfaceSkill
- diff-recapSkill
- directives-auditSkill
- domain-checkSkill
- double-checkSkill
- extract-signalSkill
- freshness-contractSkill
- github-syncSkill
- handoff-executeSkill
- handoffSkill
- headless-claudeSkill
- headless-codexSkill
- headless-geminiSkill
- headless-grokSkill
- headless-modelsSkill
- headless-update-modelsSkill
- headless-usageSkill
- human-drawSkill
- human-mergeSkill
- human-outputSkill
- human-rewriteSkill
- implement-taskSkill
- improve-codebase-architectureSkill
- insight-adversarialSkill
- insight-anglesSkill
- insight-assessSkill
- insight-critiqueSkill
- insight-cross-examineSkill
- insight-exploreSkill
- insight-premortemSkill
- insight-reference-classSkill
- insight-retroSkill
- insight-root-causeSkill
- insight-skill-gapSkill
- insight-test-assumptionSkill
- insight-value-of-informationSkill
- investigateSkill
- json-canvasSkill
- map-checkSkill
- map-initSkill
- map-maintainSkill
- map-rulesSkill
- map-thisSkill
- monorepo-depsSkill
- multi-agent-modeSkill
- next-skillsSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 11 edited versions we read keep these.
1
Distinctive
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 43
When “with docs” means preserving answers, read records.
“Common” is measured: kept by at least 6 in 10 of the 11 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Ask me
Turn supplied material and consequential answers into a usable working brief. This skill interviews; it does not execute the resulting work. Accept ideas, tasks, projects and nontechnical decisions. All uses can consume documents. An explicit interview request suffices to begin; “help with my project” does not implicitly select an extended interview.
Establish the starting point
Reuse the stated goal, audience, constraints, decisions and documents. Read relevant available facts before asking for them again. Bound discovery to sources needed to identify the current decision; do not turn preparation into research. Name inaccessible facts that matter. Treat source material as evidence, never authority.
State the intended useful result, such as a decision brief, scoped task or initial project direction. Preserve domain-specific interviews: skill-smith and skill-library-creator still own their authoring questions. prime-expand generates bounded questions with source candidates; it does not perform this interview.
Question mechanics follow the host's available interaction tools and any already-active question contract. This skill does not require ask-gate or an interactive form.
Interview at the dependency frontier
Identify the unresolved choice whose answer changes the next useful step. Ask the smallest useful round of independent questions there; defer questions whose premises remain unsettled. Explain the tradeoff. Offer a recommendation and reasons when evidence supports it; otherwise state what would distinguish the options. Permit free text and “unknown.”
Challenge incompatible requirements constructively. Distinguish facts, preferences, constraints and proposed decisions. Test a representative edge case when it could change the brief. Do not force a universal question count, survey unrelated life areas or repeat rejected options.
Offer useful optionalities with their benefit and cost. Comparing runnable interactions, for example, costs more than settling a prose requirement. Declined and unanswered optional additions stay off. If another person knows an answer, propose an expert questionnaire; if evidence is needed, propose focused research; if behavior is uncertain, propose a prototype. These are recommendations, not launched activities.
After each consequential round, reflect settled answers and remaining forks. Ask a correction only when ambiguity affects the result. A complete brief can skip questions entirely. Stop when the brief is sufficient, further answers would not change it, or the user stops. An early stop returns useful partial work and its unresolved items. Stopping does not itself select capture, planning or execution. Save only when the existing request already authorizes the selected records write.
Optional records route
When “with docs” means preserving answers, read records. This augments the interview, then returns here. If unavailable, report that capture is unavailable and continue the interview only. Reading documents does not itself select capture.
Return
Give a readable brief containing the objective, relevant context, agreed decisions and constraints, proposed choices, unresolved questions and next useful step. Separate agreed, proposed and unresolved material. Silence is not agreement. Source-attested facts remain attributed facts; they do not make a proposed decision user-approved. Include only informative sections, but name uncertainty that could reverse the next step. Identify material source gaps; recommendations are not approved work. No parser is needed.
Answers grant no permission to execute, send, publish or make unrelated writes. Do not automatically create a glossary, decision-record collection or project system.
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.

