interview-me
Skill0 starsChanged 12 days agoMITView on GitHub
Turn a fuzzy goal into a structured, living plan doc — by interview (the architect) or quick capture (Hermes). Use for a "help me plan / think this through" request or the //plan command. (Named to avoid a builtin `plan` skill.)
98 other projects use a version of this.
Adopted by
Most recently taken up by
- thistleknot/skillstheir own version, first seen Nov 8, 2026
- ishandutta2007/Awesome-Agent-Skillstheir own version, first seen Nov 8, 2026
- pedrohcgs/claude-code-my-workflowtheir own version, first seen Nov 8, 2026
- resonatingloop/hmmariumtheir own version, first seen Nov 8, 2026
- ggoosen/Digital-Workforcetheir own version, first seen Nov 8, 2026
- MMACABRE/SKILLStheir own version, first seen Nov 8, 2026
Used with
Projects with it also use constraint-driven-development, idea-refine and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
MrCipherSmithSkillconstraint-driven-development
Use when a project needs a persistent, measurable quality bar — starting a project without documented standards, 'set up constraints', or when coverage/perf/a11y thresholds get re-debated per-PR. Produces CONSTRAINTS.md with enforceable numbers, ratchets, and a guard against silent weakening. NOT for throwaway prototypes or a one-off CI setup.
Also in 16 projects that use this
LLl0k0laDSkillidea-refine
Refine ideas through structured divergent and convergent thinking. Use "idea-refine" or "ideate" to trigger.
Also in 42 projects that use this
LLl0k0laDSkillusing-agent-skills
Use when starting a session or when you need to discover which skill applies to the current task. This is the meta-skill that governs how all other skills are discovered and invoked.
Also in 32 projects that use this
HK-hubSkillobservability-and-instrumentation
Instruments code so production behavior is visible and diagnosable. Use when adding logging, metrics, tracing, or alerting. Use when shipping any feature that runs in production and you need evidence it works. Use when production issues are reported but you can't tell what happened from the available data.
Also in 32 projects that use this
orenluxySkillimplementation-notes
Maintain an IMPLEMENTATION_NOTES.md decision log during any multi-step implementation session. Use this in EVERY session that involves writing or modifying code across more than one file, or any session expected to run longer than a few tool calls. Records decisions, deviations from plan, and open questions so nothing is silently guessed.
Also in 3 projects that use this
HK-hubSkilldeprecation-and-migration
Manages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when deciding whether to maintain or sunset existing code.
Also in 29 projects that use this
- +6 more from LLl0k0laD
Other versions98 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 98
- addyosmani/agent-skills★ 114ksame name
- pedrohcgs/claude-code-my-workflow★ 1.7ksame name
- kdlbs/kandev★ 1.1ksame name
- Neeeophytee/finding-unknowns-skills★ 339same name
- flonat/flonat-research★ 150same name
- maxwell2732/paper-replicate-agent-demo★ 134same name
- maxwell2732/my-submission-formatting-agent★ 106same name
- PaulRBerg/agent-skills★ 104same name
- c-kick/hnl-agent-skills★ 56same name
- Sorbh/interview-me★ 52same name
88 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 repository14 other files it gives its agents.
- captureSkill
- capture-to-inboxSkill
- escalate-to-architectSkill
- file-noteSkill
- janitorSkill
- migrateSkill
- process-inboxSkill
- recallSkill
- resumeSkill
- scanSkill
- selftestSkill
- taskSkill
- weekly-reviewSkill
- learn-acceleratorSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.
0
Common
Most of the 84 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 23
Run the planner: the plan tool (idea-planner plugin), or python $MYOS_ENGINES/idea_plan.py "<goal>".
- Very specific: line 34
Close the loop: when it stabilizes: reflect the next action into Active Threads.md and, if durable, a project memory + MEMORY.md line.
- Distinctive: line 45
Never block a question batch on a fact you can verify yourself — check the vault/code first.
“Common” is measured: kept by at least 6 in 10 of the 84 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
interview-me
Turns "I have a bunch of ideas but need structure" into a living plan document. Two tiers, split the myOS way — The architect plans, Hermes captures. Background/why + the proven interview method: [[NOTES]].
When to Use
- A "help me plan / think this through / turn these ideas into a plan" request.
- The
//plan <goal>command.
Procedure
Hermes tier — capture (offline, deterministic). Hermes does not run an adaptive interview (a small model can't); it captures and hands off:
- Run the planner: the
plantool (idea-planner plugin), orpython $MYOS_ENGINES/idea_plan.py "<goal>". Returns goal → milestones → steps. - Save as a stub plan note (frontmatter below,
status: drafting), with an## Open questionslist and a top note: "captured by Hermes — needs the architect to interview & refine." escalate-to-architectwith the goal + the stub's path. Done — don't attempt the real planning.
The architect tier — the interview (the real value). A structured interview that ends in a plan the user can react to:
- Ground first — run
resume/ read the relevant memory so questions aren't naive. - Interview in small batches — 1–4 questions at a time, as options the user reacts to (reacting beats a blank page). Always allow "Other"/free text. Recommend, don't survey — recommended option first, say why.
- After every batch: write it down. Lock decided items, flag open ones as
- [ ], update the doc, bump a version line in## Log. - Make the user sequence — if the answer is "all of them," the next question is "which first?"
- Surface constraints honestly (feasibility, portability, what the tools actually do) as you go.
- Preserve their voice — structure the ideas, don't rewrite them.
- Close the loop when it stabilizes: reflect the next action into
Active Threads.mdand, if durable, a project memory +MEMORY.mdline.
Artifact format (the plan doc)
- Location: system/AI/cross-cutting →
<architect_memory>/Plan — <Topic>.md; single-project →projects(python $MYOS_ENGINES/myos_paths.py get projects). - Frontmatter:
title,type: plan,tags(architect+ topic),updated: YYYY-MM-DD,status: drafting|active|paused. - Body: a
> [!abstract]"what this is" + version/status line; Decided sections; Open questions as checkboxes; recommendation tables where there's a stack/choice; a dated## Logat the bottom (onevX.Yline per pass). Link related memories with[[…]].
Pitfalls
- Plans are documents, not just chat — if it wasn't written to the doc, it didn't happen.
- Decisions are the user's — the architect recommends, never delivers the verdict.
- This skill writes plans/notes only — never executes the plan's file-moves or system changes.
- Never block a question batch on a fact you can verify yourself — check the vault/code first.
- The Hermes planner has no myOS context → for internal goals it can treat myOS terms as external products. Treat the Hermes capture as a rough seed only; the architect corrects it on refine. (See [[NOTES]].)
Verification
- A plan doc exists at the right location with valid frontmatter and a dated
## Logentry for this pass. - Decided items are locked; open ones are
- [ ]checkboxes — nothing decided was left ambiguous.
Cadence
On demand. Triggers: a plan / interview-me request, or //plan <goal>.
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.

