proactive-awareness
Skill0 starsChanged 9 days agoMITView on GitHub
Applies read-only context recovery and project artifact delivery checks. Use when continuity, worktree state, active goals, or repository deliverable verification may change the response.
In this repository66 other files it gives its agents.
- AGENTS.mdAGENTS.md
- skills/bootstrap-project/resources/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- skills/bootstrap-project/resources/CLAUDE.mdCLAUDE.md
- act-tenetsSkill
- adversarial-reviewSkill
- annotate-screenshotSkill
- anti-hallucinationSkill
- ascii-chartSkill
- assess-brainSkill
- big-ideaSkill
- bootstrap-coreSkill
- bootstrap-projectSkill
- browser-toolsSkill
- chart-big-ideaSkill
- chart-interpretationSkill
- chart-vocabularySkill
- code-reviewSkill
- communication-craftSkill
- compile-brainSkill
- convertSkill
- corpus-qa-sweepSkill
- critical-thinkingSkill
- deep-reviewSkill
- doc-hygieneSkill
- docs-shellSkill
- docx-to-mdSkill
- ethical-reasoningSkill
- evaluate-before-adoptingSkill
- figure-generatorSkill
- flint-chartSkill
- flint-interactionsSkill
- flint-themeSkill
- git-workflowSkill
- html-to-mdSkill
- humanizerSkill
- install-visual-companionsSkill
- lint-clean-markdownSkill
- markdown-mermaidSkill
- markdown-sanitization-chainSkill
- md-to-emlSkill
- md-to-htmlSkill
- md-to-txtSkill
- md-to-wordSkill
- meditationSkill
- mutation-testingSkill
- planSkill
- platform-awarenessSkill
- print-svg-style-guideSkill
- problem-framing-auditSkill
- project-capability-authoringSkill
- project-statusSkill
- render-chartSkill
- render-verifySkill
- rich-emailSkill
- risk-analysisSkill
- security-and-hardeningSkill
- setup-dependenciesSkill
- setup-enterprise-stackSkill
- spikeSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
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
- Very specific: line 24
Run the read-only session-artifact checker (node <this-skill>/scripts/check-session-artifacts.cjs --repository-root <repo>) to detect …
- Very specific: line 28
Use --session <id> to bound a task-specific check when its session is known.
≈ “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
Read-only Project Recovery
Use relevant native session history, resume, and memory interfaces as secondary evidence, not as the authoritative task backlog. Read current repository guidance, HANDOFF current state/next action/blockers/verification, and the authoritative task list; use TODO.md only as a fallback. Follow existing project conventions and do not invent absent records.
This skill is read-only. Do not create or rewrite project records, instructions, memory, or installed configuration. A request to recover context does not authorize meditation writes. New topics and irrelevant/stale history must not be forced onto the user's current task.
A policy-denied source remains unavailable: do not ask the user to paste, supply, or reupload its contents, or recover them through another channel. Ask only for an independently authorized task goal or next action without restricted content. Modified does not establish staged or unstaged status; keep unobserved worktree details unknown.
Load and follow the project recovery procedure for the selected recovery, worktree-state, or focus case. Count changes with git; privacy-sensitive nudges disclose counts, not filenames. Silence wins during frustration or flow, and unsolicited reminders must be relevant and nonintrusive.
For session/context mechanics use native controls and the session boundary; do not collect cross-session behavioral scores. Missing history/handoff is a named limitation, not evidence that no work exists. Return material state, blockers, next action, and evidence without claiming fresh verification from stale notes.
Delivery-check mode
Load and follow the shared storage and delivery contract
to verify the approved task's artifact inventory, final repository files,
dependencies, discoverability, ignore state, and actual Git state.
Run the read-only session-artifact checker
(node <this-skill>/scripts/check-session-artifacts.cjs --repository-root <repo>)
to detect deliverables stranded in ~/.copilot/session-state/<id>/files/ for
the active repository.
Use --session <id> to bound a task-specific check when its session is known.
The checker verifies Git-visible copies and supported recovery manifests;
ignored copies do not satisfy delivery. Missing/corrupt manifests fail explicitly.
Absent sessions, linked paths, unsupported formats, and no matching scope are
not reported as clean. Exact-hash pruning decisions in a custody manifest can
account for deliberately retired artifacts, not changed source content.
This mode is also read-only: report missing delivery rather than relocating,
archiving, committing, or activating files without the task's write authority.
Recovery should report relevant externally stranded artifacts, not silently
promote them or treat missing session history as proof of completeness.
Runtime contract references
Load only the reference selected by the triggering instruction; do not replay all runtime contracts for unrelated work. These references add no authority and do not call the instruction again.
- recovery: session-health-monitoring
- delivery-check: project artifact storage
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.

