Skills.
Give your AI a better way to work.
A skill is a set of written instructions that teaches an AI how to do one job the way it should be done: review a pull request, plan a migration, write the release notes.
Install one here and it travels with your account into Claude, Claude Code, Cursor and every other client you sign in with.
Category: Dev tools
16,980 results · page 160 of 566
- View details
clarify-resourcesSkillDev tools
Understand what resources the user has available for research — compute,
Ready to connect★ 469
- View details
clarify-specSkillDev tools
Full execution protocol for MODE: CLARIFY-SPEC -- resolving spec clarification markers and maintaining spec/planning alignment.
Ready to connect★ 469
- View details
classification-navigationSkillDev tools
IPC/CPC hierarchy drill-down and lateral expansion for patent discovery
Ready to connect★ 469
- View details
closest-worldsSkillDev tools
'Strategy: Lewis Possible Worlds — find the minimal change to reality
Ready to connect★ 469
- View details
clr-validationSkillDev tools
Apply Goldratt's 8 Categories of Legitimate Reservation to validate causal
Ready to connect★ 469
- View details
cluster-analysisSkillDev tools
Identify natural opinion clusters from collected judgments and characterize
Ready to connect★ 469
- View details
coherence-diagnosisSkillDev tools
Strategy for auditing preference consistency using Consistency Ratio,
Ready to connect★ 469
- View details
cold-startSkillDev tools
Full crystallization strategy for users who have no research direction
Ready to connect★ 469
- View details
collective-adjudicationSkillDev tools
Strategy for multi-judge ranking aggregation using Condorcet, Schulze,
Ready to connect★ 469
- View details
combination-enumerationSkillDev tools
SOP for systematically enumerating combinations across dimensions.
Ready to connect★ 469
- View details
combination-evaluationSkillDev tools
Evaluate new combinations for feasibility and novelty
Ready to connect★ 469
- View details
combinatorial-creativitySkillDev tools
Combinatorial Creativity Campaign — produce emergent concepts via concept
Ready to connect★ 469
- View details
combinatorial-synthesisSkillDev tools
Synthesize all combinatorial creativity outputs
Ready to connect★ 469
- View details
comparative-feasibility-rankingSkillDev tools
Compare feasibility across multiple candidates using multi-dimensional
Ready to connect★ 469
- View details
comparative-formulationSkillDev tools
'Strategy: Construct comparative research questions — systematic comparison
Ready to connect★ 469
- View details
comparison-executorSkillDev tools
Execute a pairwise comparison between two candidates, producing a judgment
Ready to connect★ 469
- View details
competing-hypothesis-constructionSkillDev tools
Strategy: Construct multiple competing hypotheses for the same phenomenon
Ready to connect★ 469
- View details
competing-hypothesis-generationSkillDev tools
SOP: Generate mechanistically distinct competing hypotheses for the same phenomenon
Ready to connect★ 469
- View details
competing-hypothesis-matrixSkillDev tools
'Tactic: Multi-hypothesis management — generate competing hypotheses,
Ready to connect★ 469
- View details
consultSkillDev tools
Full execution protocol for MODE: CONSULT -- answering advisory questions with bounded evidence and clear uncertainty.
Ready to connect★ 469
- View details
critic-gateSkillDev tools
Full execution protocol for MODE: CRITIC-GATE -- plan critic review, revision loops, and hard stop before execution.
Ready to connect★ 469
- View details
deep-diveSkillDev tools
Full execution protocol for MODE: DEEP_DIVE — read-only codebase audit with parallel explorer waves, 2 independent reviewers, and sequential critic challenge for HIGH/CRITICAL findings. Loaded on demand by the architect when the deep-dive command emits a [MODE: DEEP_DIVE ...] signal.
Ready to connect★ 469
- View details
deep-researchSkillDev tools
Full execution protocol for MODE: DEEP_RESEARCH — orchestrator-worker deep research over external sources: decompose, iterative web_search/web_fetch retrieval, parallel sme synthesis, dual-reviewer claim verification, critic challenge of high-stakes claims, and a cited report. Loaded on demand by th
Ready to connect★ 469
- View details
engineering-conventionsSkillDev tools
Codex adapter for opencode-swarm engineering invariants. Use before modifying plugin initialization, subprocesses, runtime portability, .swarm containment, plan durability, test_runner behavior, test-writing patterns, session/global state, guardrails/retry semantics, chat/system hooks, tool registra
Ready to connect★ 469
- View details
ensure-all-tests-pass-after-code-changesSkillDev tools
ensure all tests pass after code changes
Ready to connect★ 469
- View details
fork-pr-operationsSkillDev tools
Operational patterns for fork PRs (head repo differs from base repo). Covers GitHub workflow approval after push, force-push protocol, remote naming conventions, stale CI verification, and bot review multi-round awareness. Load when working with fork PRs, cross-repo contributions, or workflow approv
Ready to connect★ 469
- View details
git-revert-safetySkillDev tools
Apply when reverting commits, undoing merges, or recovering from branch contamination. Covers collateral damage verification (manifest, package.json, CHANGELOG, lockfiles), cherry-pick vs revert decision matrix, partial-revert detection, merge-parent handling, and post-revert CI verification. Preven
Ready to connect★ 469
- View details
guardrail-patternsSkillDev tools
Codex adapter for opencode-swarm destructive-command guardrail changes. Use before modifying src/hooks/guardrails.ts, checkDestructiveCommand, dcNormalizeCommand, shell-wrapper parsing, .swarm destructive-command blocking, or guardrails unit/adversarial tests.
Ready to connect★ 469
- View details
isolate-the-specific-failure-mode-before-proposing-a-fixSkillDev tools
isolate the specific failure mode before proposing a fix
Ready to connect★ 469
- View details
issue-ingestSkillDev tools
Full execution protocol for MODE: ISSUE_INGEST -- GitHub issue intake, localization, spec generation, and transition to the full fix workflow.
Ready to connect★ 469
What is a skill?
A skill is plain text, usually a SKILL.md file and the scripts it refers to, written for an AI rather than for a person. It carries the steps, the house rules and the examples a good answer needs, so you stop pasting the same briefing into every new chat.
53,462 of the 53,895 skills listed here can be served through ahel today, and they come from public repositories. Each one has its own page with the instructions themselves on it, so you can read what a skill will tell your AI to do before you install it.
Install one and every AI you use gets it
Installing a skill adds it to your gateway and turns it on in the same step. Claude Code surfaces it as a slash command; any client can read the full instructions with the skill_read tool.
Nothing is copied into a project folder. The instructions are served from your account, so the same skill is there in every AI you connect, and turning it off removes it from all of them at once.