{"id":51015963,"url":"https://github.com/drubinstein/terry","last_synced_at":"2026-06-21T10:30:50.504Z","repository":{"id":362191555,"uuid":"1257182178","full_name":"drubinstein/terry","owner":"drubinstein","description":"A collection of Claude Code skills for general software-engineering work — bug reproduction (jamie), root-cause debugging (sherlock), performance (brendan), empirical iteration (andrej), and agent-fleet orchestration (terry).","archived":false,"fork":false,"pushed_at":"2026-06-14T21:39:15.000Z","size":142,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-06-14T23:15:17.667Z","etag":null,"topics":["agentic-coding","claude-code","claude-code-plugin","claude-code-skills","debugging","developer-tools"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/drubinstein.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-06-02T12:46:06.000Z","updated_at":"2026-06-14T21:39:19.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/drubinstein/terry","commit_stats":null,"previous_names":["drubinstein/terry"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/drubinstein/terry","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/drubinstein%2Fterry","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/drubinstein%2Fterry/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/drubinstein%2Fterry/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/drubinstein%2Fterry/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/drubinstein","download_url":"https://codeload.github.com/drubinstein/terry/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/drubinstein%2Fterry/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34607126,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-21T02:00:05.568Z","response_time":54,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agentic-coding","claude-code","claude-code-plugin","claude-code-skills","debugging","developer-tools"],"created_at":"2026-06-21T10:30:48.213Z","updated_at":"2026-06-21T10:30:50.490Z","avatar_url":"https://github.com/drubinstein.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Claude Code skills for software engineering\n\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)\n\nA small collection of Claude Code **skills** — reusable, named methodologies for\neveryday engineering work. Each is a self-contained playbook (a `SKILL.md` plus\noptional references and templates) that Claude loads on demand when your request\nmatches it.\n\n## Why this exists\n\nClaude writes code well but, under pressure, tends to *guess* — skip reproducing a\nbug, theorize before measuring, dismiss a failure as \"flaky,\" or call something\ndone without evidence. Each skill here encodes a disciplined methodology that\nresists exactly that, distilled from real long-running agent work. You invoke one\nby intent — \"does this bug actually reproduce?\", \"find the bottleneck\" — and\nClaude follows the matching playbook.\n\n## The skills\n\n| Skill | What it does |\n|-------|--------------|\n| **[jamie](skills/jamie/SKILL.md)** | Confirms a bug report actually reproduces before you fix it. |\n| **[sherlock](skills/sherlock/SKILL.md)** | Finds the cause of a stubborn bug by elimination. |\n| **[brendan](skills/brendan/SKILL.md)** | Finds the bottleneck when something is slow (Brendan Gregg's USE method). |\n| **[andrej](skills/andrej/SKILL.md)** | Drives an iterative fix or tuning loop, gated on a metric. |\n| **[terry](skills/terry/SKILL.md)** | Runs many long-running agent tasks as a paced queue — parallelized and merged, with concurrency capped to avoid OOM and pace token spend. |\n| **[ronald](skills/ronald/SKILL.md)** | Runs a controlled A/B experiment to choose a model or prompt. |\n\nMost stand alone, but five compose into a debugging-to-fix pipeline: **jamie**\n(confirm it's real) → **sherlock** (find the cause) → **brendan** (find the\nbottleneck) → **andrej** (drive the fix, gated on a metric) → **terry** (run many\nat once, paced to your machine and budget). **ronald** stands apart — a controlled\nexperiment for picking a model or prompt with evidence. See each skill's\n`SKILL.md` for the full method.\n\n## Example\n\nYou paste a bug report: *\"CSV export corrupts my file every time.\"* Claude recognizes\na triage task and loads **jamie** — which stops it from closing the issue after one\ngreen run on the latest build. Instead it matches the reporter's version and file,\nreproduces the crash at their data scale, and minimizes it to a one-command repro:\n**CONFIRMED**. It hands that repro to **sherlock** to eliminate suspects down to the\nroot cause, then to **andrej** to drive the fix, gated on the repro until it passes.\n\n## Using these skills\n\n**As a plugin** — point your Claude Code plugin config at this repo (or a marketplace\nentry that references it). The manifest at `.claude-plugin/plugin.json` auto-discovers\nevery `skills/*/SKILL.md`.\n\n**As personal skills** — copy any skill directory into your user skills folder:\n\n```bash\ncp -R skills/sherlock ~/.claude/skills/sherlock   # or any other skill\n```\n\nEither way, Claude auto-discovers them and loads the right one when your request\nmatches its description — or invoke one explicitly with the Skill tool.\n\n## Layout\n\nEach skill is a directory under `skills/`:\n\n```\nskills/\u003cname\u003e/\n  SKILL.md        # the methodology — what it's for and how to run it\n  references/     # deeper detail, loaded on demand (optional)\n  templates/      # copy-paste worksheets / scripts (optional)\n```\n\nThe repo is named `terry` for historical reasons — it began as that single\nagent-fleet skill — but it's now a general collection, and `terry` is just one\nskill in it.\n\n## Contributing\n\nEach skill follows the same shape — a tight `SKILL.md` with depth in `references/`\nand copy-paste assets in `templates/` — and is built test-first: write a failing\nscenario for a subagent, write the skill, then close the loopholes it finds. New\nskills and fixes are welcome via pull request or\n[issues](https://github.com/drubinstein/terry/issues).\n\n## License\n\n[MIT](LICENSE) © David Rubinstein\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdrubinstein%2Fterry","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdrubinstein%2Fterry","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdrubinstein%2Fterry/lists"}