agentleFS
BhaskarManamBhaskarManam/pstack/skills/challenge/SKILL.md

challenge

Skill4 starsChanged 7 months agoMITView on GitHub

Generate a CEO/CPO-level provocation grounded in the user's current project artifacts and user profile. Appends to CHALLENGES.md. One per day.

33 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use prove-it, ingest and 9 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.
  • Neko-Catpital-LabsSkill

    prove-it

    Shared evidence rule for investigating, diagnosing, debugging, proving, or explaining what happened or why for any problem or situation: do not assert something is fixed, working, passing, merged, or running unless you personally observed it this turn and can show what you saw; do not assert it was caused by X until a repro and controlled isolation prove that cause.

    Also in 3 projects that use this

  • JaimeGBASkill

    ingest

    Digest an external source (article, paper, transcript, URL, book chapter) and integrate its content into the knowledge base

    Also in 4 projects that use this

  • MetaSkill

    roadmap

    Build, continue, inspect, or visualize a source-grounded mathematical roadmap and theorem DAG in an existing Autoform Markdown blueprint. Use for source research, repository-wide inventories of existing and planned mathematics, scope, coverage, milestones, and roadmap articles; do not create repository infrastructure or prove Lean declarations.

    Also in 3 projects that use this

  • genomewalkerSkill

    learn

    Learn from web sources, generate SKILL.md, and store key patterns in soul memory. Trigger keywords: learn, skill-gen, web-learn, documentation, tutorial.

    Also in 4 projects that use this

  • AnthropicSkill

    start

    Set up your bio-research environment and explore available tools. Use when first getting oriented with the plugin, checking which literature, drug-discovery, or visualization MCP servers are connected, or surveying available analysis skills before starting a new project.

    Also in 3 projects that use this

  • Hugging FaceSkill

    implement

    Make tests pass. Invoke after /write-tests produces failing tests.

    Also in 5 projects that use this

The file

Show its rules and text

We split this skill into the rules it gives an agent

15 rules. 0 are common, 5 are distinctive, and 10 are very specific to this project.

  • 0

    Common

    Most of the 29 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 10

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read pstack-workspace/{slug}/CHALLENGES.md if it exists.

    line 16
  2. Very specific:

    If a challenge was generated today (same date): tell the user: *"You've already had today's challenge.

    line 18
  3. Very specific:

    Read skills/challenge/config.yaml — cadence, categories, format rules.

    line 25
  4. Very specific:

    Read ~/.config/pstack/user-profile.yaml — the user's purpose, ikigai, values, customer archetypes.

    line 26
  5. Very specific:

    Read the most recent artifacts in pstack-workspace/{slug}/:

    line 27
  6. Very specific:

    Read the last 5 challenges from CHALLENGES.md (if exists) — avoid repeating category or framing.

    line 31
  7. Very specific:

    Read knowledge/INDEX.md — identify which frameworks are most relevant to the current project state.

    line 32
  8. Distinctive:

    Use WebSearch (up to 2 queries) to gather current market context relevant to the product:

    line 38
  9. Distinctive:

    Write a CEO/CPO-level provocation:

    line 63
  10. Very specific:

    Personalized: if user-profile.yaml exists, weave in their ikigai, purpose, or customer archetype

    line 69
  11. Distinctive:

    Create the file if it doesn't exist.

    line 90
  12. Very specific:

    Write ~/.config/pstack/last-session.md per knowledge/schemas/last-session.schema.md.

    line 102
  13. Distinctive:

    Never generate more than one challenge per day unless explicitly overridden with "force"

    line 108
  14. Distinctive:

    Do not end with advice or a to-do list — end with a question

    line 110
  15. Very specific:

    If user-profile.yaml doesn't exist, the challenge is still grounded in artifacts.

    line 111

“Common” is measured: kept by at least 6 in 10 of the 29 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

/challenge

You generate one CEO/CPO-level provocation per day. Not a how-to. Not encouragement. A hard question or uncomfortable truth grounded in the user's actual work — the kind a board member or brutal honest mentor would ask.


Step 1 — Rate limit check

Read pstack-workspace/{slug}/CHALLENGES.md if it exists. Check the date of the most recent challenge.

  • If a challenge was generated today (same date): tell the user: "You've already had today's challenge. Come back tomorrow — or run it again with /challenge force to override."
  • Unless the user said "force", stop here.

Step 2 — Read context

  1. Read skills/challenge/config.yaml — cadence, categories, format rules.
  2. Read ~/.config/pstack/user-profile.yaml — the user's purpose, ikigai, values, customer archetypes.
  3. Read the most recent artifacts in pstack-workspace/{slug}/:
    • 00-vision.md (if exists)
    • 02-prd.md (if exists)
    • 03-design-brief.md (if exists)
  4. Read the last 5 challenges from CHALLENGES.md (if exists) — avoid repeating category or framing.
  5. Read knowledge/INDEX.md — identify which frameworks are most relevant to the current project state.

Step 3 — Research (WebSearch)

Use WebSearch (up to 2 queries) to gather current market context relevant to the product:

  • What are competitors doing in this space right now?
  • What recent customer research, trend reports, or industry news is relevant?
  • What's changed in this market in the last 6 months?

Ground the challenge in real-world context — not just the artifact content.


Step 4 — Select category

From config.yaml categories, choose the one least covered in recent challenges AND most relevant to the current project state:

StateBest category
DRAFT_VISION / VISION_DONEstrategy, customer
DRAFT_STRATEGY / STRATEGY_DONEstrategy, priorities
DRAFT_PRD / PRD_DONEcustomer, priorities
DRAFT_BRIEF / BRIEF_DONErevenue, priorities
Anyreflection (rotate in periodically)

Step 5 — Draft the challenge

Write a CEO/CPO-level provocation:

  • Grounded: cite something specific from the user's artifacts or user-profile
  • Hard: asks the question the user might be avoiding
  • Short: 200–350 words
  • Not a how-to: ends with a question, not a prescription
  • Personalized: if user-profile.yaml exists, weave in their ikigai, purpose, or customer archetype

Structure:

  1. Opening hook — state the uncomfortable truth or the hidden assumption
  2. Evidence — name what in the artifact or market context makes this real
  3. The question — one sharp closing question the user must sit with

Step 6 — Append to CHALLENGES.md

Append to pstack-workspace/{slug}/CHALLENGES.md:

## Challenge — {YYYY-MM-DD} ({category})

{challenge text}

---

Create the file if it doesn't exist.


Step 7 — Present to user

Show the challenge in full. Do not add commentary or soften it. The challenge should land as written.


Step 8 — Write last-session.md

Write ~/.config/pstack/last-session.md per knowledge/schemas/last-session.schema.md.


Rules

  • Never generate more than one challenge per day unless explicitly overridden with "force"
  • The challenge must cite something specific from the user's work or context — not generic wisdom
  • Do not end with advice or a to-do list — end with a question
  • If user-profile.yaml doesn't exist, the challenge is still grounded in artifacts; just less personalized
  • CHALLENGES.md is gitignored by default — it's the user's private strategic journal, not a public artifact

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.