Skip to content

sergeyklay/.agents / .agents/skills/improve-self

improve-self

Verified

Detect when a missing Agent Skill would have made the current task faster or more reliable, then scaffold a candidate SKILL.md for user review. Use after a non-trivial task when one of these signals fires: the same procedure repeated 3+ times, error recovery required inventing a workflow, the user corrected the approach (not the answer), the agent realized mid-task that a playbook did not exist, or 5+ tool calls produced what should have taken 1-2. Detects which `.{vendor}/` directories exist on the host (project and home), reads every skill and slash command in them before proposing, and never duplicates. Writes candidates into the project's .{vendor}/skills/{name} directory that the running host actually loads, never the home folder. Do NOT use for first-attempt failures, one-off questions, fact gaps that belong in research, or style gaps that belong in rules files. Pass the trace and the signal that fired as arguments; the skill does not reconstruct them from the conversation.

references/alternatives-to-a-skill.md

View on GitHub
# Alternatives to a new skill

Load this only when the candidate fails one of Phase 3's four criteria (Procedural / Reusable / Self-contained / Testable), or when the gap looks skill-shaped but lives more naturally elsewhere. Route the gap to its proper home — do not force it into a skill.

| Gap shape | Better home |
|---|---|
| A project convention everyone needs to know | `AGENTS.md` |
| A coding-style rule | `.agents/rules/` or the platform's `rules/` directory |
| A one-off task with no future recurrence | Document in the current conversation; nothing persists |
| A fact about an external API | The research path next time (see `research-it`); do not hardcode |
| A capability the agent cannot do at all (auth, write-API call against a private system) | Propose an MCP server, not a skill |
| A user-triggered template with arguments | A slash command (`.agents/commands/`, `.claude/commands/`, or the platform's equivalent) |
| A repeated investigation pattern in one domain | A skill — proceed |
| A recurring explanation pattern for one topic class | A skill — proceed |

When in doubt, prefer the smaller intervention. Skills are tokens that load forever.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 323kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 323kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 323kUpdated Claude CodeCodexVerifiedInstall