pstack-status
Skill4 starsChanged 7 months agoMITView on GitHub
Dashboard across all pstack projects: current state, artifact rubric scores, staleness, last challenge date. Read-only snapshot.
In this repository18 other files it gives its agents.
- bhaskar-reviewSkill
- cagan-reviewSkill
- challengeSkill
- critiqueSkill
- design-briefSkill
- julie-reviewSkill
- lenny-reviewSkill
- north-starSkill
- onboardSkill
- opportunitySkill
- prdSkill
- pstack-helpSkill
- pstack-learnSkill
- pstack-upgradeSkill
- ravi-reviewSkill
- shreyas-reviewSkill
- strategySkill
- visionSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
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
- Distinctive: line 81
After the dashboard, list:
- Very specific: line 91
If no projects are found, tell the user how to start: *"No pstack projects found.
- Very specific: line 92
Do not hallucinate artifact scores — only report what's in .pstack-meta.json.
≈ “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.
Files
/pstack-status
You generate a read-only status dashboard across all pstack projects the user is working on.
Step 1 — Discover projects
Scan pstack-workspace/ in the current directory for subdirectories containing .pstack-meta.json.
Also check any additional project directories if the user mentions them.
Step 2 — Read each project
For each project directory found, read:
.pstack-meta.json— project name, slug, state, artifact list with scores and dates- The most recent artifact modification dates from the filesystem
CHALLENGES.md— date of the most recent challenge (if file exists)
Step 3 — Compute staleness
An artifact is stale if it was last modified more than 14 days ago and the project is in an incomplete state (not BRIEF_DONE).
A challenge is overdue if the last challenge was more than 1 day ago (daily cadence) or 7 days ago (weekly cadence).
Step 4 — Present the dashboard
Format:
## pstack status — {YYYY-MM-DD}
────────────────────────────────────────────────
### {Project Name} [{slug}]
State: {STATE_MACHINE_STATE}
Last active: {N} days ago
Artifacts:
✓ 00-vision.md score: {X.X}/5 ({YYYY-MM-DD}) {STALE? ⚠️}
✓ 01-strategy.md score: {X.X}/5 ({YYYY-MM-DD})
○ opportunity-{bet}.md score: {X.X}/5 ({YYYY-MM-DD}) (optional, per-bet)
✓ 02-prd.md score: {X.X}/5 ({YYYY-MM-DD})
✗ 03-design-brief.md (not started)
Reviews: {N} reviews in reviews/
Last challenge: {YYYY-MM-DD} — {N} days ago {OVERDUE? ⚠️}
Next recommended action: {one-line recommendation based on state}
────────────────────────────────────────────────
### {Project 2 Name} ...
────────────────────────────────────────────────
Summary:
{N} project(s) active
{N} artifact(s) below passing floor (< 3.5) — consider /critique
{N} challenge(s) overdue — run /challengeStep 5 — Surface recommendations
After the dashboard, list:
- Any artifact with score below 3.5 → recommend
/critiqueand then revision - Any project with stale artifacts → recommend resuming
- Any overdue challenges → recommend
/challenge
Rules
- This skill is read-only — it never writes to any artifact or meta file (except last-session.md)
- If no projects are found, tell the user how to start: "No pstack projects found. Run
/visionin your project directory to begin." - Do not hallucinate artifact scores — only report what's in
.pstack-meta.json. If score is missing, show as "unscored — run /critique"
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.

