Weekly Engineering Retro
garrytan/gstack
Builds a weekly engineering retrospective from git history: commit counts, per-person contributions, work patterns and code quality numbers over a chosen window.
Retrospective on a coding session that proposes changes to the agent's environment (checks, pointers, steering, tooling) so the next run goes better.
Install Retro
$ npx skills add sammcj/agentic-coding --skill retro -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install sammcj/agentic-coding retro --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/sammcj/agentic-coding.git skills-src && mkdir -p .claude/skills && cp -r skills-src/Skills/retro .claude/skills/retro && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "retro" agent skill from https://github.com/sammcj/agentic-coding/tree/main/Skills/retro into .claude/skills/retro/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "retro", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/sammcj/agentic-coding/tree/main/Skills/retroType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add sammcj/agentic-coding --skill retro -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install sammcj/agentic-coding retro --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sammcj/agentic-coding.git skills-src && mkdir -p .agents/skills && cp -r skills-src/Skills/retro .agents/skills/retro && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "retro" agent skill from https://github.com/sammcj/agentic-coding/tree/main/Skills/retro into .agents/skills/retro/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "retro", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add sammcj/agentic-coding --skill retro -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install sammcj/agentic-coding retro --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sammcj/agentic-coding.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/Skills/retro .cursor/skills/retro && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "retro" agent skill from https://github.com/sammcj/agentic-coding/tree/main/Skills/retro into .cursor/skills/retro/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "retro", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/sammcj/agentic-coding.git --path Skills/retro--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add sammcj/agentic-coding --skill retro -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install sammcj/agentic-coding retro --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sammcj/agentic-coding.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/Skills/retro .gemini/skills/retro && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "retro" agent skill from https://github.com/sammcj/agentic-coding/tree/main/Skills/retro into .gemini/skills/retro/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "retro", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install sammcj/agentic-coding retroInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add sammcj/agentic-coding --skill retro -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/sammcj/agentic-coding.git skills-src && mkdir -p .github/skills && cp -r skills-src/Skills/retro .github/skills/retro && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "retro" agent skill from https://github.com/sammcj/agentic-coding/tree/main/Skills/retro into .github/skills/retro/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "retro", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add sammcj/agentic-coding --skill retro -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install sammcj/agentic-coding retro --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sammcj/agentic-coding.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/Skills/retro .opencode/skills/retro && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "retro" agent skill from https://github.com/sammcj/agentic-coding/tree/main/Skills/retro into .opencode/skills/retro/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "retro", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
retro- GitHub stars
- 162
- Token cost
- ~1.2k tokens
- SKILL.md length
- 639 words
- Files
- 2 (incl. scripts)
- Skills in repo
- 64
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Retrospective on a coding session that proposes changes to the agent's environment (checks, pointers, steering, tooling) so the next run goes better.
- Works in 6 steps: Create a task per step below, each with… → Get the session record → Mark the struggle moments: errors,… → …
- Tasks that involve Retrospectives
- SKILL.md covers Steps, Categories, Placement and Applying a picked candidate
- Runs Python scripts from its folder; calls python3
What it does
Retro is an agent skill from sammcj/agentic-coding. Retrospective on a coding session that proposes changes to the agent's environment (checks, pointers, steering, tooling) so the next run goes better.
Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts (for example `scripts/session_digest.py`). Compatibility notes: claude-code
It sits in Product & Project Management, covering Retrospectives. The repository describes itself as: Agentic Coding Rules, Templates etc... The licence is Apache-2.0.
When your agent uses it
- Tasks that involve Retrospectives
Example prompts
- “/retro”
Requirements
- Python 3
- Compatibility (from SKILL.md): claude-code
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Create a task per step below, each with its completion criterion.
- Get the session record
- Mark the struggle moments: errors, retries, hook blocks, long searches, oversized results, compactions, user corrections, wrong turns…
- Read the repo's existing checks (Makefile, package.json scripts, pre-commit config, CI workflows, .claude/settings.json hooks). A check…
- Map each struggle moment to a candidate using the categories below. Drop any candidate you can't trace to a struggle moment.
- Present candidates ranked by severity: cost of the struggle times how often it will recur. Each candidate states the moment, the fix, and…
What it can do on your machine
Read from SKILL.md and the folder at commit 2f25ced. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
python3
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Compatibility
claude-code
From compatibility in the SKILL.md frontmatter.
Context cost
Retro loads about 1.2k tokens when it runs. Until then it costs about 39 tokens; SKILL.md has 639 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from sammcj/agentic-coding at commit 2f25ced, republished under its Apache-2.0 licence (© sammcj). 639 words, ~1,169 tokens.
Download SKILL.mdSave it as
.claude/skills/retro/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- retro
- description
- Retrospective on a coding session that proposes changes to the agent's environment (checks, pointers, steering, tooling) so the next run goes better.
- compatibility
- claude-code
- disable-model-invocation
- true
- argument-hint
- [session-id or transcript path]
- metadata.source
- https://github.com/mattpocock/skills (adapted)
Retro
Propose improvements to the agent's environment based on where a session struggled. Propose only: change nothing until the user picks a candidate. Fix the environment, not the code the session produced (that is code-review).
Steps
- Create a task per step below, each with its completion criterion.
- Get the session record:
- No session named: use the current conversation.
- Session named, or the current one is too long to recall reliably: run
python3 scripts/session_digest.py <id-or-path>(--list N --project <repo>to find it). Digest each subagent transcript it lists when the struggle happened there.
- Mark the struggle moments: errors, retries, hook blocks, long searches, oversized results, compactions, user corrections, wrong turns. Cite each by digest call number (
#12) or by quoting the user. - Read the repo's existing checks (
Makefile,package.jsonscripts, pre-commit config, CI workflows,.claude/settings.jsonhooks). A check that exists but is unwired or broken is the finding, in place of a new one. - Map each struggle moment to a candidate using the categories below. Drop any candidate you can't trace to a struggle moment.
- Present candidates ranked by severity: cost of the struggle times how often it will recur. Each candidate states the moment, the fix, and the file it lands in.
Categories
- Navigation: the agent took long to find a file or fact. Fix: a pointer from a file it already reads.
- Automated checks: the agent made a mistake a tool could catch. Fix: lint rule, type, test, pre-commit hook, CI job, or a Claude Code PreToolUse/PostToolUse hook. A repo with no guardrail (no pre-commit hook and no CI running lint/typecheck/test) is a finding in itself.
- Coding standards: the reviewer missed a mistake. Classify it first. Mechanical (banned API, import shape, file location, fixed syntax) gets a deterministic check. Judgement call (cross-file consistency, matching surrounding style) goes in the repo's standards doc (
CODING_STANDARDS.mdorCONTRIBUTING.md).code-reviewreads only what the repo documents, so a new standards doc also needs a one-line pointer from the projectCLAUDE.md. - Steering bloat: global
~/.claude/CLAUDE.md, projectCLAUDE.md/AGENTS.md,.claude/rules/, auto-memoryMEMORY.md, SessionStart hook context, or model-invoked skill descriptions are large. Fix: move instructions into checks or standards, path-scope them into rules, or tighten a skill description or make it user-invoked. - No-ops: steering lines the agent already obeys by default, or ignored anyway. Fix: delete, or replace with a check. Treat each as a candidate for the deletion test, judged on one session.
- Skills: a skill failed to fire, fired wrongly, or its instructions misled the agent. Fix: its description or body.
- Tool economy: a tool call was expensive for what it returned (see oversized results in the digest), or the agent repeated a call. Fix: a cheaper command, a script, or a narrower tool.
- Information access: the agent lacked information it needed. Fix: tee dev server logs to a file, read-only access to a service, a docs pointer.
- Sandbox and permissions: a sandbox or hook block cost retries. Fix: the command pattern the agent should have used, or a sandbox/permission rule change for the user to make.
Show full SKILL.md (131 more words)Show less
Placement
The implementer has the most context pressure: it explores, writes code and debugs. The reviewer gets a diff. Put rules where there is room to apply them.
- Steering files (
CLAUDE.md,AGENTS.md, SessionStart hooks) load into every session. Reserve them for navigation pointers and rules that apply to every task. - A recurring mistake becomes a failing check before it becomes prose.
- Judgement rules go to the reviewer's standards doc, not
CLAUDE.md. Extend an existing doc before writing a new one. - A user preference correction belongs in auto-memory as a
feedbackmemory. Repo facts belong in the repo.
Applying a picked candidate
Load the matching skill before editing:
CLAUDE.mdor.claude/rules/->authoring-claude-md- A skill ->
skill-creator-primer - Hooks, permissions or settings ->
update-config
Run a proposed check against the repo before letting it block anything.
© sammcj, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file (scripts) in Skills/retro of sammcj/agentic-coding.
- SKILL.md
- scripts/session_digest.py
Open the folder on GitHubat commit 2f25ced
Compare with similar skills
Retro next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Retro this skillsammcj/agentic-coding | 162 | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | |
| Weekly Engineering Retrogarrytan/gstack | 136k | — | ~2.4k | Automated safety check: Pass | MIT | |
| Dough Execute Planterryyin/lizard | 2.6k | — | ~4.3k | Automated safety check: Pass | Custom licence | |
| Oral Paper SkillAdkid-Zephyr/oral-paper-skill | 350 | — | ~1.9k | Automated safety check: Pass | None | |
| Deck Retroasheshgoplani/agent-deck | 1k | — | ~1.8k | Automated safety check: Pass | MIT | |
| Dough Execution Retrospectiveterryyin/lizard | 2.6k | — | ~4k | Automated safety check: Pass | Custom licence |
Similar skills
Dough Execute Plan
terryyin/lizard
Executes one selected story or bounded retrospective correction through an executable plan, or one authorized planless slice from a selected simple story or a contextual instruction, with…
Oral Paper Skill
Adkid-Zephyr/oral-paper-skill
Help authors learn from exemplary ICLR, ICML, and NeurIPS papers through source-linked manuscript comparisons, concrete writing and experiment suggestions, and guided reflection.
Deck Retro
asheshgoplani/agent-deck
Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs.
Dough Execution Retrospective
terryyin/lizard
Reviews planned, completed planless quick, or quick-to-planned execution against original intent, aggregate commits, current whole-product architecture, and tests, including after cleanup.
Criticism Self Criticism
HughYau/qiushi-skill
批评与自我批评：在工作完成、阶段验收、收到批评或同类错误反复出现时，对成果和过程做诚实、具体、基于事实的审视，输出可执行的改进项，并处理外来批评而不辩解。触发信号包括 review、复盘、审查、"帮我看看有没有问题"、"你确定吗"；任务刚开始或只是单步查询时不触发。
More from sammcj/agentic-coding
All 64 skills in this repoYue2 Music
sammcj/agentic-coding
A skill your agent uses when generating songs with YuE2, covering a recording via SheetSage2 audio-to-ABC, editing a score or lyrics with melody preservation, or building a reproducible listening…
Bento Slides
sammcj/agentic-coding
A skill your agent uses when creating or editing Bento (.bento.html) slide decks, including any request for a single-file HTML slide deck.
Idrive Backup
sammcj/agentic-coding
A skill your agent uses whenever the user wants you to manage, discuss or diagnose iDrive Backup configuration on macOS
Piper Tts Training
sammcj/agentic-coding
Train custom TTS voices for Piper (ONNX format) using fine-tuning or from-scratch approaches.
PPTX To Md
sammcj/agentic-coding
Convert a PPTX slide deck into per-slide markdown that preserves both the verbatim text and the meaning of embedded screenshots, diagrams and charts in their original layout positions.
Skill Creator Primer
sammcj/agentic-coding
You MUST load this skill before the skill-creator skill AND before making ANY change to, or conducting a review of ANY Agent Skill.
Related
Categories
Questions about Retro
What does Retro do?
Retrospective on a coding session that proposes changes to the agent's environment (checks, pointers, steering, tooling) so the next run goes better. Retro is an agent skill from sammcj/agentic-coding. Retrospective on a coding session that proposes changes to the agent's environment (checks, pointers, steering, tooling) so the next run goes better.
When should I use Retro?
Retro fits situations like: tasks that involve Retrospectives.
How do I install Retro in Claude Code?
Run `npx skills add sammcj/agentic-coding --skill retro -a claude-code`. Or copy the skill folder (Skills/retro in sammcj/agentic-coding) into .claude/skills/retro in your project. Claude Code loads it when a task matches its description.
How do I install Retro in Codex?
Run `npx skills add sammcj/agentic-coding --skill retro -a codex`. Or copy the skill folder (Skills/retro in sammcj/agentic-coding) into .agents/skills/retro in your project. Codex loads it when a task matches its description.
Can I use Retro in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add sammcj/agentic-coding --skill retro -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/retro, .gemini/skills/retro, .github/skills/retro and .opencode/skills/retro in your project.
What does Retro need to run?
Going by SKILL.md and its folder, Retro needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3. Compatibility (from SKILL.md): claude-code.
Does Retro access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Retro safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Retro use?
Retro is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Retro use?
About 1.2k tokens (SKILL.md is roughly 4.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Retro?
Skills that share tags, products or a category with Retro: Weekly Engineering Retro (garrytan/gstack, 136k stars), Dough Execute Plan (terryyin/lizard, 2.6k stars), Oral Paper Skill (Adkid-Zephyr/oral-paper-skill, 350 stars) and Deck Retro (asheshgoplani/agent-deck, 1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Retro?
sammcj (a GitHub user) maintains it in sammcj/agentic-coding, which has 162 GitHub stars. The repository holds 64 skills in this directory. The repository was last updated on October 9, 2026.
Source: sammcj/agentic-coding on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.