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.
A skill your agent uses when the user runs /retro or explicitly requests a session retrospective.
Install Retro
$ npx skills add kdlbs/kandev --skill retro -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install kdlbs/kandev 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/kdlbs/kandev.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/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/kdlbs/kandev/tree/main/.agents/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/kdlbs/kandev/tree/main/.agents/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 kdlbs/kandev --skill retro -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install kdlbs/kandev retro --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kdlbs/kandev.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/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/kdlbs/kandev/tree/main/.agents/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 kdlbs/kandev --skill retro -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install kdlbs/kandev retro --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kdlbs/kandev.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/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/kdlbs/kandev/tree/main/.agents/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/kdlbs/kandev.git --path .agents/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 kdlbs/kandev --skill retro -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install kdlbs/kandev retro --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kdlbs/kandev.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/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/kdlbs/kandev/tree/main/.agents/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 kdlbs/kandev 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 kdlbs/kandev --skill retro -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/kdlbs/kandev.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/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/kdlbs/kandev/tree/main/.agents/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 kdlbs/kandev --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 kdlbs/kandev retro --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kdlbs/kandev.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/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/kdlbs/kandev/tree/main/.agents/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
- 909
- Token cost
- ~1.6k tokens
- SKILL.md length
- 876 words
- Files
- 2
- Skills in repo
- 45
- Repo updated
- First seen
- Licence
- AGPL-3.0
At a glance
A skill your agent uses when the user runs /retro or explicitly requests a session retrospective.
- Works in 5 steps: Gather session evidence → Filter candidates → Choose the shared source → …
- The user runs /retro
- SKILL.md covers 1. Gather session evidence, 2. Filter candidates, 3. Choose the shared source and 4. Report and stop, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Retro is an agent skill from kdlbs/kandev. Use when the user runs /retro or explicitly requests a session retrospective. Find session lessons and propose concrete shared harness edits for future efficiency. Exclude memory files. Do not run unprompted.
Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `template.md`).
It sits in Product & Project Management, covering Retrospectives. The repository describes itself as: AI Kanban & Development Environment. Orchestrate multiple agents, review changes, open PRs. Multi-provider, self-hostable, no telemetry. The licence is AGPL-3.0.
When your agent uses it
- The user runs /retro
- Explicitly requests a session retrospective
Example prompts
- “/retro”
Workflow steps
5 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit b734113. 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
No scripts in the folder and no shell commands in SKILL.md.
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.
Context cost
Retro loads about 1.6k tokens when it runs. Until then it costs about 54 tokens; SKILL.md has 876 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); files beside SKILL.md are not scanned.
SKILL.md
The full file from kdlbs/kandev at commit b734113, republished under its AGPL-3.0 licence (© kdlbs). 876 words, ~1,621 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
- Use when the user runs /retro or explicitly requests a session retrospective. Find session lessons and propose concrete shared harness edits for future efficiency. Exclude memory files. Do not run unprompted.
Retro
Run this workflow only when the user explicitly requests a retrospective. A natural-language request is sufficient. Review the current session for lessons that improve future agent sessions. By default, propose edits in the reply and stop. Do not edit files during the retrospective. If the user explicitly requests edits as part of the retro, apply the qualifying changes within that authorization. Do not commit, push, open a PR, or create persistent tasks unless the user explicitly requests those actions.
Optional focus: /retro commit or /retro apps/backend/AGENTS.md limits the analysis to that workflow, topic, or path.
1. Gather session evidence
Use the available conversation, tool results, user corrections, and files touched in this session. If the user identifies another session, use its available primary sources instead. If context is incomplete, state that limitation. Do not invent missing events or search unrelated private transcripts.
Look for:
- Repeated failed commands, retries, dead ends, or unnecessary exploration.
- Missing navigation pointers, hidden dependencies, or ambiguous workflow instructions.
- Excessive output, repeated reads, lost tool handles, or avoidable context consumption.
- Successful techniques that saved work and can apply to other tasks.
- User corrections that reveal a reusable process gap.
Separate observed events from possible causes. Verify each proposed cause against current files or authoritative documentation. Do not infer a permanent user preference from a single correction. Do not mine unrelated PR reviews or perform a general repository audit.
2. Filter candidates
Keep a candidate only if it passes every test:
- Behavior change: Identify the earlier decision that the proposed guidance changes and how that change improves the outcome.
- Recurrence: The same gap can affect a normal future session on different code.
- Cost: The gap risks correctness, security, contracts, performance, or substantial wasted tool calls and rework.
- Specificity: State one concrete, testable action with its trigger. Include a fallback or verification where necessary.
- No duplication: Read the proposed target and search related guidance before proposing an edit.
If existing instructions already cover the gap, skip another rule. Tighten unclear wording only if that ambiguity caused the miss. Remove or shorten ineffective guidance only if session evidence supports that change. Skip common knowledge, one-off filenames, task IDs, temporary paths, secrets, cosmetic preferences, and rules already enforced by automated checks. Do not turn a temporary tool workaround into a permanent instruction without evidence that it remains necessary. Prefer an empty action list over weak lessons. Do not fill a quota.
Show full SKILL.md (470 more words)Show less
3. Choose the shared source
Use harness-improvement for artifact placement and validation. Read its session-learnings reference for normalization and deduplication. Load only the artifact or platform references relevant to surviving candidates.
Eligible targets are shared repository harness files:
.agents/skills/, shared commands, agents, review guidance, and harness scripts.- The closest scoped
AGENTS.md, or rootAGENTS.mdfor a rule that applies across the repository. - Existing repository platform instructions, settings, and hooks in
.claude/,.codex/,.cursor/, or.opencode/.
Route workflow lessons to the owning skill before considering always-on instructions. Prefer a small correction to an existing rule over a new file. Propose a new skill only for a repeatable workflow with no existing owner. Keep the repository's single-session and delegation policies intact unless the user explicitly authorizes a change.
Exclude memory files, auto-memory, transcript notes, personal settings, application code, application tests, CI, specifications, ADRs, and plans. Do not save the retrospective to disk. If a lesson requires product changes, identify the limitation in the reply without adding a harness action. If the fix belongs to an uneditable tool or hosted service, report it separately under Upstream. Do not propose a brittle harness workaround for an upstream defect.
Resolve symlinks before choosing an edit path. Use .agents/skills/ and AGENTS.md as this repository's shared sources.
Edit AGENTS.md directly. Preserve the CLAUDE.md symlink to it.
Do not copy skill changes into platform mirrors or create new platform trees.
If a real platform file needs a distinct change, read the corresponding harness-improvement platform reference first.
Measure target line, word, and byte counts. Stay within the limits in its validation reference.
If a target exceeds its limit, propose a replacement or a narrower home instead of appending more text.
4. Report and stop
Use template.md for the reply. Use today's date and keep the sections brief.
Connect each proposed action to an observed event and its expected benefit.
Order actions by impact. Each checkbox needs a repository-relative source path and an exact addition, replacement, or removal.
For a replacement, show the current text and the proposed text. Avoid vague actions such as "improve the docs."
If no candidate survives, write None. under Action Items.
Include Upstream only if an observed problem belongs there.
If edits lack authorization, return the proposals and stop. State that the user can request all edits or select individual items. Do not treat silence or an unanswered question as authorization.
5. Apply authorized edits
Re-read the accepted targets and re-check duplication before editing. Apply only accepted changes. Preserve unrelated work and match the target file's voice. Keep session evidence in the reply and reusable directives in the shared files. Run the checks in harness validation for the changed files. Report each edited path, the concrete change, and validation results. If an accepted change is redundant or no longer valid, explain why you skipped it.
© kdlbs, AGPL-3.0. 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 in .agents/skills/retro of kdlbs/kandev.
- SKILL.md
- template.md
Open the folder on GitHubat commit b734113
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 skillkdlbs/kandev | 909 | — | ~1.6k | Automated safety check: Pass | AGPL-3.0 | |
| Weekly Engineering Retrogarrytan/gstack | 136k | — | ~2.4k | Automated safety check: Pass | MIT | |
| Dough Execute Planterryyin/lizard | 2.5k | — | ~4.3k | Automated safety check: Pass | Custom licence | |
| After Action Reportrampstackco/claude-skills | 940 | 1 repos | ~2.5k | Automated safety check: Pass | MIT | |
| Oral Paper SkillAdkid-Zephyr/oral-paper-skill | 340 | — | ~1.9k | Automated safety check: Pass | None | |
| Deck Retroasheshgoplani/agent-deck | 1k | — | ~1.8k | Automated safety check: Pass | MIT |
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…
After Action Report
rampstackco/claude-skills
Run a structured after-action review (postmortem, retrospective) on a launch, incident, or completed project to capture timeline, root cause analysis, contributing factors, and actionable lessons.
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.
More from kdlbs/kandev
All 45 skills in this repoPR Walkthrough
kdlbs/kandev
Generate a single-file HTML walkthrough that explains a PR's purpose, user impact, interface changes, compatibility risks, and implementation.
Debug
kdlbs/kandev
Diagnose Kandev bugs, running-instance issues, UI/browser failures, and runtime behavior.
Harness Improvement
kdlbs/kandev
Improve Kandev's AI harness from session learnings or explicit requests.
Diagram Design
kdlbs/kandev
Create branded architecture, IT current-state, flowchart, sequence, state machine, ER/data model, timeline, swimlane, quadrant, radar/spider, polar chart (polar/radial lollipop), loop/flywheel…
TDD
kdlbs/kandev
Implement changes using Test-Driven Development (Red-Green-Refactor).
Verify
kdlbs/kandev
Run a broad local verification audit only when the user explicitly requests it or PR/CI remediation requires it.
Related
Categories
Questions about Retro
What does Retro do?
A skill your agent uses when the user runs /retro or explicitly requests a session retrospective. Retro is an agent skill from kdlbs/kandev. Use when the user runs /retro or explicitly requests a session retrospective.
When should I use Retro?
Retro fits situations like: the user runs /retro; explicitly requests a session retrospective.
How do I install Retro in Claude Code?
Run `npx skills add kdlbs/kandev --skill retro -a claude-code`. Or copy the skill folder (.agents/skills/retro in kdlbs/kandev) 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 kdlbs/kandev --skill retro -a codex`. Or copy the skill folder (.agents/skills/retro in kdlbs/kandev) 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 kdlbs/kandev --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?
SKILL.md names no scripts, command-line tools or credentials: Retro is instructions for the agent only.
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. Review the folder before installing.
What licence does Retro use?
Retro is published under the AGPL-3.0 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 1.6k tokens (SKILL.md is roughly 6.5k 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, 2.5k stars), After Action Report (rampstackco/claude-skills, 940 stars) and Oral Paper Skill (Adkid-Zephyr/oral-paper-skill, 340 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Retro?
kdlbs (a GitHub organization) maintains it in kdlbs/kandev, which has 909 GitHub stars. The repository holds 45 skills in this directory. The repository was last updated on October 8, 2026.
Source: kdlbs/kandev on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.