SkillRepo
Sign InSign Up
Catalog
Yeachan-Heo/recall

Yeachan-Heo

recall

Reconstruct working context from artifacts in trust order — state files, notepad, verification ledger, decision trail, transcript tail — then report where work stands and the next action. After a break or crash.

v1.0LATEST
NewUpdated Nov 8, 2026

Recall

Reconstruct where the work stands from what was persisted, in order of trust:

  1. Durable state: .omc/notepad.md, .omc/project-memory.json, and the per-mode state in both active layouts (ralph/autopilot/team) — the session-scoped .omc/state/sessions/{id}/ and the legacy .omc/state/<mode>-state.json fallback for runs persisted before a session id existed (docs/HOOKS.md keeps both live) — what was in flight, what iteration, what was blocked.
  2. Ledgers and trails: under OMC's state root — the verification ledger (state/verification-ledger.tsv, by default the checkout's .omc/state/; OMC_STATE_DIR or a parent .omc-workspace moves the root) and every state/decision-trail-*.tsv file (what was decided and why); enumerate the glob before reconstructing.
  3. The transcript tail: the last N messages of this session — what was said, what was promised.
  4. The shared record: the repo's standing rules (AGENTS.md/CLAUDE.md) name project-specific places to check before declaring anything "never recorded".

Report

  • Where it stands: one paragraph, from the state files.
  • What was last proven: from the ledger, with SHAs.
  • Open threads: promised-but-not-done, from the transcript and trails.
  • The next action: one concrete step, named — then take it if the user asked for continuation, propose it if they asked for status.

Rules

  • Report from the artifacts, not from memory; memory is what the artifacts are for.
  • A thread with no artifact behind it is reported as "mentioned but not persisted", never reconstructed from vibes.
  • Human rulings encountered in the trails keep their original wording (why skill epistemics).
Files1
1 files · 1.0 KB

Select a file to preview

Overall Score

78/100

Grade

B

Good

Grades are signals, not a certification. Always review a skill yourself before use.

Safety

85

Quality

75

Clarity

82

Completeness

68

Summary

The Recall skill reconstructs working context from persisted artifacts (state files, ledgers, transcripts, decision trails) to report where work stands and identify the next action. It reads from a structured state directory (`.omc/`) and project memory files, then synthesizes a status report without modifying files.

Detected Capabilities

file readjson parsingtsv parsingmarkdown parsingcontext synthesis

Trigger Keywords

Phrases that agents use to match this skill to user intent.

resume work after crashreconstruct session contextverify from state filescheck project memoryresume interrupted task

Risk Signals

INFO

Reads from `.omc/` directory structure including session-scoped state files

Section: Durable state, bullet 1
INFO

Accesses verification ledger and decision trail TSV files in state root

Section: Durable state, bullet 2
INFO

Reads transcript tail from session messages

Section: Durable state, bullet 3
INFO

References external project rules (AGENTS.md/CLAUDE.md) for context

Section: The shared record, bullet 4

Referenced Domains

External domains referenced in skill content, detected by static analysis.

github.com

Use Cases

  • Resume work after session interruption or crash
  • Reconstruct context from verified decision trail and ledgers
  • Verify progress against persisted state files rather than memory
  • Identify blocked tasks or promised-but-unfinished work
  • Reconstruct debugging or problem-solving session state

Quality Notes

  • Clear purpose and scope: reconstructs context from artifacts rather than attempting speculative recovery
  • Well-defined trust hierarchy for artifact prioritization, making the reconstruction deterministic
  • Explicitly states limitation: 'A thread with no artifact behind it is reported as mentioned but not persisted'
  • References external documentation (HOOKS.md, AGENTS.md, CLAUDE.md) but instructions remain self-contained
  • State directory paths are environment-aware (respects OMC_STATE_DIR, .omc-workspace convention)
  • Preserves human reasoning from decision trails: 'Human rulings encountered in the trails keep their original wording'
  • Output structure is concrete: where-it-stands, what-was-proven, open-threads, next-action
  • One minor gap: does not specify error handling if key artifact files are missing or corrupted
Model: claude-haiku-4-5-20251001Analyzed: Nov 8, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Use Yeachan-Heo/recall in your dev environment

Start a Developer trial

Command Palette

Search for a command to run...