SkillForge

agent-observability

src/skillforge/builtin_skills/agent-observability/SKILL.md

Instrument agent tool calls, prompt latency, token expenditure, and error boundaries with structured OpenTelemetry or JSON-L logging. Use when debugging agent loops or optimizing multi-agent tracing.

antislop-code

src/skillforge/builtin_skills/antislop-code/SKILL.md

Enforce rigorous code comment hygiene, anti-overengineering constraints, and eliminate AI-generated narrative filler while preserving valuable domain invariants. Use when reviewing code, refactoring modules, or auditing pull requests.

blast-radius-containment

src/skillforge/builtin_skills/blast-radius-containment/SKILL.md

Analyze upstream callers, downstream dependencies, and enforce strict minimal-diff boundaries before modifying shared code. Use when modifying core utilities, database models, public API signatures, or widely imported types.

caveman

src/skillforge/builtin_skills/caveman/SKILL.md

Ultra-terse, high-density technical communication mode that reduces output tokens while preserving technical accuracy, exact commands, and safety warnings. Use when concise responses or lower token consumption is desired.

code-review

src/skillforge/builtin_skills/code-review/SKILL.md

Conduct disciplined multi-pass adversarial code reviews assessing correctness, security, performance, and test coverage. Use when reviewing diffs, pull requests, or staged changes before merging.

cognitive-loop-breaker

src/skillforge/builtin_skills/cognitive-loop-breaker/SKILL.md

Detect and interrupt trial-and-error death spirals where repetitive edits fail tests across consecutive turns. Enforce a mandatory hypothesis reset and clean git rollback. Use when stuck in recurring test failures or repetitive debugging loops.

context-compactor

src/skillforge/builtin_skills/context-compactor/SKILL.md

Distill extensive agent session transcripts into dense knowledge states, active hypothesis ledgers, and verified file citation indices. Use when context windows approach limits or during multi-agent handoffs.

contract-test-generator

src/skillforge/builtin_skills/contract-test-generator/SKILL.md

Author property-based fuzz tests and contract invariants to verify edge cases, serialization symmetry, and boundary conditions. Use when testing schemas, parser logic, or public library APIs.

dependency-upgrade

src/skillforge/builtin_skills/dependency-upgrade/SKILL.md

Manage methodical dependency updates with changelog and advisory review, incremental version bumps, automated regression test runs, and rollback plans. Use when updating packages, resolving security vulnerabilities, or modernizing outdated toolchains.

flaky-test-isolation

src/skillforge/builtin_skills/flaky-test-isolation/SKILL.md

Diagnose and eliminate non-deterministic test failures caused by async race conditions, unseeded randoms, state leakage, or clock skew. Use when tests fail intermittently in CI or pass inconsistently.

git-workflow

src/skillforge/builtin_skills/git-workflow/SKILL.md

Standardize Git hygiene with atomic conventional commits, pre-staging diff inspections, protected branch guardrails, and conflict pause protocols. Use when staging changes, writing commits, or resolving branch divergences.

human-in-the-loop

src/skillforge/builtin_skills/human-in-the-loop/SKILL.md

Enforce explicit human approval boundaries before executing irreversible actions, deploying code, modifying schemas, or making external financial/data mutations. Use when building safe autonomous agent workflows.

mcp-tool-designer

src/skillforge/builtin_skills/mcp-tool-designer/SKILL.md

Architect high-performance, type-safe Model Context Protocol (MCP) servers and tools with strict JSON schemas, token bounds, idempotent annotations, and decoupled error reporting. Use when designing MCP tools or building AI agent integrations.

performance-profiler

src/skillforge/builtin_skills/performance-profiler/SKILL.md

Isolate latency bottlenecks, N+1 query patterns, memory allocations, and algorithmic complexity regressions using baseline-first measurement. Use when optimizing slow endpoints, high CPU/memory usage, or database queries.

runtime-api-verification

src/skillforge/builtin_skills/runtime-api-verification/SKILL.md

Introspect installed packages, verify method signatures, and inspect type definitions before invoking unfamiliar third-party library APIs. Use when integrating third-party SDKs, upgrading dependencies, or resolving import errors.

secret-sanitizer

src/skillforge/builtin_skills/secret-sanitizer/SKILL.md

Audit staged files, commit diffs, and terminal outputs for leaked API keys, tokens, and private credentials. Use when preparing git commits, staging code changes, or configuring environment variables.

security-threat-modeler

src/skillforge/builtin_skills/security-threat-modeler/SKILL.md

Map trust boundaries, attack surfaces, object-level authorization (IDOR/BOLA), SSRF vectors, and injection sinks before shipping backend or agent endpoints. Use when reviewing security, designing APIs, or auditing auth flows.

self-improving-agent

src/skillforge/builtin_skills/self-improving-agent/SKILL.md

Extract concrete lessons and operational heuristics from runtime failures, user corrections, and test cycles into durable project memory. Use when capturing recurring debugging patterns or user preferences.

skill-architect

src/skillforge/builtin_skills/skill-architect/SKILL.md

Design, author, and refactor SKILL.md packages, AGENTS.md catalogs, and CLAUDE.md instructions using progressive disclosure and context-budget discipline. Use when creating or optimizing agent skills and instruction files.

spec-driven-development

src/skillforge/builtin_skills/spec-driven-development/SKILL.md

Design systems contract-first using typed schemas, OpenAPI/JSON-Schema models, and failing test harnesses before writing application logic. Use when architecting new modules, APIs, or data models.

summarize

src/skillforge/builtin_skills/summarize/SKILL.md

Distill complex engineering documents, logs, and pull request diffs into structured executive summaries with citations and key architectural decisions. Use when summarizing technical repositories or code reviews.

supply-chain-sentinel

src/skillforge/builtin_skills/supply-chain-sentinel/SKILL.md

Verify third-party package existence, registry metadata, age, and CVE status before installing dependencies. Use when adding packages, upgrading libraries, or editing requirements and lockfiles.

systematic-debugging

src/skillforge/builtin_skills/systematic-debugging/SKILL.md

Execute a disciplined four-phase root-cause investigation loop (Reproduce, Isolate, Hypothesize, Surgical Patch) before modifying code. Use when diagnosing failing tests, runtime crashes, race conditions, or performance regressions.

tavily-search

src/skillforge/builtin_skills/tavily-search/SKILL.md

Execute targeted web research across high-trust primary sources, official documentation, and technical repositories. Use when researching cutting-edge library APIs, SDKs, or current industry standards.

test-driven-development

src/skillforge/builtin_skills/test-driven-development/SKILL.md

Enforce rigorous Red-Green-Refactor development cycles with automated test runner discovery, failing reproduction assertions, and raw terminal exit criteria. Use when implementing new features, writing bug reproductions, or refactoring existing modules.

zero-downtime-migration

src/skillforge/builtin_skills/zero-downtime-migration/SKILL.md

Plan and execute non-breaking database schema changes, table reorganizations, and API payload updates using the Expand-Contract pattern. Use when modifying SQL tables, ORM models, or public API endpoints in production systems.