agentleFS
aradmanamnaoonaradmanamnaoon/vibe-coding-skills/skills/agent-reliability/project-context-recovery/SKILL.md

project-context-recovery

Skill0 starsChanged 19 days agoMITView on GitHub

Reconstruct an interrupted project's goals, current state, completed work, and next safe actions from repository evidence. Use after context loss, compaction, session changes, or handoff.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read applicable repository instructions before edits.

    line 20
  2. Distinctive:

    Read repository instructions and current Git status before making changes.

    line 33
  3. Distinctive:

    Run a cheap health check only when it helps distinguish stale documentation from current behavior.

    line 37
  4. Distinctive:

    Do not reset/clean or overwrite ambiguous uncommitted work during recovery.

    line 47
  5. Distinctive:

    No completed work is redundantly reimplemented.

    line 52
  6. Distinctive:

    If a decision existed only in an unavailable prior conversation, state that it cannot be recovered from repository evidence and avoid …

    line 64

≈ “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

Purpose

Resume without restarting or duplicating completed work.

When to activate

A coding session was interrupted or the current agent lacks reliable project history.

When not to activate

The repository is new and no prior work exists.

Preconditions

  • Read applicable repository instructions before edits.
  • Preserve unrelated working-tree changes and establish a baseline when the workflow can modify code.
  • Identify which tools and environments are actually available; do not claim unavailable checks ran.

Required inputs

  • Repository instructions
  • Git status/log/branches
  • Plans/issues/docs
  • Recent tests/artifacts

Workflow

  1. Read repository instructions and current Git status before making changes.
  2. Inspect recent commits/diffs and task/plan files to infer what has actually been completed.
  3. Locate authoritative prompt/spec/issue references in the repository or supplied context.
  4. Build a concise state ledger: objective, completed evidence, in-progress uncommitted work, blockers, pending requirements.
  5. Run a cheap health check only when it helps distinguish stale documentation from current behavior.
  6. Continue from the first unsupported requirement; do not recreate files/features already present and validated.
  7. Persist a compact handoff artifact when the project explicitly benefits from portable continuity.

Relevant tools

Git, repository search, task docs/issues, test commands.

Safety restrictions

Do not reset/clean or overwrite ambiguous uncommitted work during recovery.

Validation

  • Recovered state matches observable Git/files/test evidence.
  • No completed work is redundantly reimplemented.
  • Pre-existing uncommitted changes remain preserved.

Expected output

  • Recovered objective/state
  • Completed evidence
  • Uncommitted ownership notes
  • Next ordered actions

Failure handling

If a decision existed only in an unavailable prior conversation, state that it cannot be recovered from repository evidence and avoid guessing destructive changes.

Completion criteria

The skill is complete only when every applicable validation item above has observed evidence or is explicitly marked not executed with the concrete blocker. Do not replace missing evidence with confidence language.

Research mapping

This skill was selected from research problems: P047. See research/vibe-coding-problems.md and research/problem-evidence.csv in the Vibe Coding Skills repository.

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.