agentleFS
ljucaskljucask/pureinn-product-development/skills/pm-reconcile-status/SKILL.md

pm-reconcile-status

Skill2 starsChanged 4 months agoMITView on GitHub

Progress dashboard for an in-flight reconciliation rebuild. Reads the Reconciliation Plan and state.json, shows which areas are done, in progress, and pending, surfaces open business-logic divergences that still need the team's decision, and routes to the next area command. Run it every time you sit down to a multi-session reconcile. Read-only - it changes nothing.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 2 are distinctive, and 5 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.

  • 5

    Very specific

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

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

    No workspace, or inputs missing: name which are missing and what each one unlocks, then offer the PREREQ paths - proceed on stated …

    line 32
  2. Very specific:

    Read pureinn-variables.md / state.json where a value is actually used, not at the top of the run.

    line 34
  3. Distinctive:

    Run it whenever you return to a reconcile in progress, before deciding what to do next.

    line 42
  4. Distinctive:

    If no plan exists, do not guess.

    line 50
  5. Very specific:

    If an area is in_progress → resume it first.

    line 88
  6. Very specific:

    If all areas are done but verify.disposal_ready is not true (or verify never ran) → next is /pm-reconcile verify (do not call the source …

    line 90
  7. Very specific:

    If all areas are done and verify.disposal_ready: true → reconciliation is complete and the source is safe to retire.

    line 91

≈ “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

PM - Reconcile Status

Agent mode (--agent)

Supports --agent: runs autonomously in a subagent, drafts the artifact from existing inputs, and returns a short summary + coverage note.

  • No flag → interactive (default); if inputs are heavy, offer agent mode.
  • --agent → obey. First check inputs are complete. Anything missing: do NOT invent it - mark [ASSUMED - what/why] in the output and summary. Never hallucinate to fill a gap.

Standalone run

Needs the artifacts listed under Dependencies - it synthesizes them, so without them there is nothing to synthesize.

  • No workspace, or inputs missing: name which are missing and what each one unlocks, then offer the PREREQ paths - proceed on stated assumptions marked [ASSUMED - what/why], or route to the skill that produces the missing input. Never hard-block, and never invent the input.
  • Writing never depends on /pureinn having run: with no workspace, create just the folder this skill writes into, or write to a path the user names, and say where the file went.
  • Read pureinn-variables.md / state.json where a value is actually used, not at the top of the run. Missing value: continue and name the capability it costs.

What this skill does

A read-only dashboard for a reconciliation rebuild driven by pm-reconcile. Because reconciliation runs across multiple sessions, this skill answers "where are we" at a glance: which areas are done, what is next, and which divergences still need a human ruling. It writes nothing.

Run it whenever you return to a reconcile in progress, before deciding what to do next.


Dependencies

  • pm-reconcile plan exists: reconcile/reconciliation_plan.md and state.json reconcile.areas[].

If no plan exists, do not guess. Tell the user:

No reconciliation plan found. Run /pm-reconcile first to inspect the docs and build the plan.

Step 1: Read state

Read state.json reconcile (machine source of truth for status) and reconcile/reconciliation_plan.md (area definitions). If they disagree, trust state.json and note the drift. Read reconcile/reconciliation_report.md to count and list open divergences (DIV-NN rows with no ruling, and any "Open questions for the team"). If a reconcile.verify block exists, read it (and coverage_report.md if present) to report disposal readiness.

Step 2: Render the dashboard

RECONCILE STATUS - [Product Name]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Scope:  [domain-by-domain / whole product]    Policy: [source-of-truth policy]
Progress: [X]/[N] areas done

 #  AREA       TARGET                                STATUS         BATCHES  DIV OPEN
 1  domain     domain/entities.md                    ✓ done         1/1      0
 2  rules      business_rules.md + decision_models   ▸ in_progress  2/5      2
 3  features   features/feature_list.md              · pending      -        -

NEEDS A TEAM DECISION (open divergences)
  DIV-03 [rules] refund window: doc 14d vs code 30d - decide fix code / update rule
  [open question from report]

SOURCE DISPOSAL (verify gate)
  [not run yet / ⚠️ not safe - 4 gaps, 2 DIV open / ✅ safe to archive - covered 100%]

NEXT
  ▸ /pm-reconcile rules        (resumes at batch 3/5 - completed batches are not redone)
  then /pm-reconcile features
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Rules for "NEXT":

  • If an area is in_progress → resume it first.
  • Else the lowest-order pending area is next.
  • If all areas are done but verify.disposal_ready is not true (or verify never ran) → next is /pm-reconcile verify (do not call the source safe to archive yet).
  • If all areas are done and verify.disposal_ready: true → reconciliation is complete and the source is safe to retire; route onward (below).

Step 3: Route

SituationOutput
Area in progress"Resume with /pm-reconcile [area]."
Next area pending"Run /pm-reconcile [area] to continue."
Open divergences block confidence"Decide DIV-NN with the team before marking rules Final; they are listed above."
All areas done, verify not yet ✅"Content first: run /pm-reconcile verify to prove the source is fully captured and incorporate any gaps before retiring it."
All areas done + verify ✅"Source safe to archive. Now form: /pm-product-roadmap (phases over the complete set) → /pm-audit (naming, metadata, descriptions - covers what verify added) → /pm-stripe for JIT delivery. Review reconciliation_report.md with the team."

Handoff


Čo si teraz má: Aktuálny obraz rekonciliácie - čo hotové, čo zostáva, ktoré divergencie čakajú na rozhodnutie tímu.

Ďalší krok: /pm-reconcile [oblasť] podľa NEXT vyššie. Keď sú všetky oblasti hotové, poradie je obsah→plán→forma: /pm-reconcile verify (dôkaz pokrytia + doplnenie medzier) → /pm-product-roadmap (fázy) → /pm-audit (forma nad kompletným setom) → /pm-stripe.

Môžeš preskočiť ak: rekonciliácia ešte nezačala — vtedy spusti /pm-reconcile (plán) najprv.

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.