agentleFS
lenar-amirovlenar-amirov/product-pipeline-public/.claude/skills/deep-think/SKILL.md

deep-think

Skill13 starsChanged 5 months agoMITView on GitHub

Facilitated partner-led thinking session for problems that are NOT initiatives yet — strategy questions, org decisions, "should we enter X" — where there is no metric gap to pipeline. The PM leads, Claude structures and executes. Use for "давай подумаем стратегически", "помоги продумать сложный вопрос", "стоит ли нам…", "как подойти к реорганизации", "think this through with me", "у меня нет метрики, но есть проблема". When the problem IS a metric gap — that's /hypotheses, not this.

14 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use ecosystem-reference, fractal-delegation 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.
  • naman10parikhSkill

    ecosystem-reference

    Quick-access directory of Claude Code ecosystem repos, skills, plugins, MCPs, and patterns. Use when improving the harness.

    Also in 5 projects that use this

  • naman10parikhSkill

    fractal-delegation

    Also in 5 projects that use this

  • roronoazoroshao369Skill

    memory-compression

    Also in 5 projects that use this

  • KirchliveSkill

    skill-routing

    Decides which of the installed skills a task needs and loads them before the work starts. This skill should be used at the beginning of any multi-step task — build, fix, refactor, migrate, review, plan, release, research, write, design, video — and again at every phase change, after context compaction, and when work moves into a different part of the codebase. Use it for requests like "let's build X", "fix this bug", "refactor Y", "plan the migration", "review this", and also when the user asks which skill applies, why a skill did not fire, or asks to check what is available.

    Also in 5 projects that use this

  • sublimotionSkill

    agent-runtime

    Launch and manage detached agent runs on EKS via the agent-runner CLI. Use when the user says "launch an agent run", "agent runtime", "agent-runner", "run this spec on the cluster", "check run status", "agent run logs", or "stop a run". Do NOT use for writing the agent-runner code itself (edit the sibling ../agent-runner repo), Terraform of the foundation (use terraform-automation), or GPU serving deployments (use infra-deployer).

    Also in 5 projects that use this

  • GoZippySkill

    repo-scout

    Also in 5 projects that use this

  • +5 more from naman10parikh

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 13 edited versions we read keep these.

  • 2

    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
  1. Distinctive:

    No fake rigor: strategy sessions run on INFERRED evidence — type it, don't dress it as analysis.

    line 38
  2. Distinctive:

    If halfway in it's clearly an initiative (metric found, segment named) — say so and switch to the pipeline instead of finishing the …

    line 40

“Common” is measured: kept by at least 6 in 10 of the 13 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.

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

Deep Think — /deep-think

A facilitated thinking session for the questions the pipeline can't hold: no metric, no funnel, often no product surface — strategy bets, org design, build-vs-buy, "is this worth an initiative at all". The PM is the partner (owns direction, makes calls); Claude is the associate (structures, drafts, stress-tests). One session, one page of output.

How to run it

  1. Frame together — restate the question until the PM confirms it's THE question; name the decision it feeds and who makes it. (For briefs handed down by a stakeholder, ambiguity-resolver does this framing.)
  2. Structure — build the tree with problem-structuring (MECE applies to strategy questions too; the root is the decision, not a metric). Present the structure, let the PM cut or reweight branches — their context beats symmetric completeness.
  3. Work the priority branches — for each surviving branch: what we know (typed honestly — most of it will be INFERRED/AMBIGUOUS here, say so), what would change the answer, cheapest way to find out.
  4. Synthesize answer-first — pyramid: recommendation → 2-3 supporting arguments → evidence and open risks. Prose per writing-style.md.
  5. Land it — one page to whatever file the PM names (or in-chat). Then the bridge, always offered, never forced:
    • the question turned out to be a metric gap → "превратить в инициативу?" (Frame + /hypotheses — the tree's branches seed the hypotheses);
    • it stays strategic → offer to bank durable conclusions in knowledge/facts.json so future initiatives inherit them.

Boundaries

  • PM decides at every fork; Claude proposes, never railroads.
  • No fake rigor: strategy sessions run on INFERRED evidence — type it, don't dress it as analysis.
  • If halfway in it's clearly an initiative (metric found, segment named) — say so and switch to the pipeline instead of finishing the ceremony.

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.