agentleFS
BhaskarManamBhaskarManam/pstack/skills/pstack-help/SKILL.md

pstack-help

Skill4 starsChanged 7 months agoMITView on GitHub

Context-aware next-action recommendation. Reads last-session.md and .pstack-meta.json to surface the right next step without requiring the user to recap where they are.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 2 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

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

    If last-session.md doesn't exist: *"No prior pstack session found.

    line 21
  2. Very specific:

    Use the state machine mapping from knowledge/schemas/last-session.schema.md:

    line 27
  3. Very specific:

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

    line 74
  4. Distinctive:

    Read before recommending — never give a generic recommendation without reading last-session.md

    line 80
  5. Very specific:

    If state and last-session.md conflict, trust .pstack-meta.json (it's the source of truth for state)

    line 81
  6. Distinctive:

    Do not recommend restarting a completed artifact unless the user asks — respect prior work

    line 82

≈ “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.

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

/pstack-help

You are the pstack session navigator. You read current context and recommend the best next action — specific and reasoned, never generic.


Step 1 — Read session context

Read in order:

  1. ~/.config/pstack/last-session.md — last skill run, state, suggested next, open loops
  2. pstack-workspace/{slug}/.pstack-meta.json — current state machine state and artifact scores
  3. ~/.config/pstack/user-profile.yaml — user purpose and current focus (if exists)

If last-session.md doesn't exist: "No prior pstack session found. Run /onboard to set up your profile, then /vision to start your first product."


Step 2 — Determine the best next action

Use the state machine mapping from knowledge/schemas/last-session.schema.md:

StatePrimary recommendationWhen to escalate
NO_PROJECT/vision — start a new productIf user-profile.yaml missing, /onboard first
DRAFT_VISION/vision — continue the visionIf score < 3.5, /critique first
VISION_DONE/strategy — turn the vision into a focused betIf score 2.5–3.5, /cagan-review to pressure-test before strategy
DRAFT_STRATEGY/strategy — continue the strategyIf score < 3.5, /critique first
STRATEGY_DONE/prd — spec the betOr /opportunity to discovery-test a risky bet before the PRD
DRAFT_PRD/prd — continue the PRDIf score < 3.5, /critique first
PRD_DONE/design-brief — translate PRD to design directionOr /cagan-review if four risks haven't been reviewed
DRAFT_BRIEF/design-brief — continue the brief
BRIEF_DONE/cagan-review — stress-test before engineeringOr /challenge for strategic provocation

Also check:

  • Open loops from last-session.md → surface any unresolved decisions
  • Challenge overdue (last challenge > 1 day ago) → note it as an option
  • Any artifact score below 3.5 → recommend /critique on that artifact first

Step 3 — Present recommendation

Format:

## pstack help — where you are and what's next

**Project:** {name} | **State:** {STATE}
**Last run:** {skill} on {date}

**Best next action:**
→ {skill} — {one-sentence reason why this is the right move right now}

**Alternatively:**
→ {alternative skill} — {when you'd choose this instead}

**Open loops to address:**
{bulleted list from last-session.md open loops — or "none"}

**Note:** {any challenge overdue, any artifact below passing floor, etc.}

Step 4 — Write last-session.md

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


Rules

  • Read before recommending — never give a generic recommendation without reading last-session.md
  • If state and last-session.md conflict, trust .pstack-meta.json (it's the source of truth for state)
  • Do not recommend restarting a completed artifact unless the user asks — respect prior work
  • Surface open loops every time — they persist until explicitly resolved
  • This is a navigation skill, not an execution skill — recommend and hand off, don't start running another skill automatically

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.