agentleFS
Yesterday-AIYesterday-AI/ytstack/skills/retro/SKILL.md

retro

Skill2 starsChanged 29 days agoMITView on GitHub

Milestone retrospective through the installed gstack retro skill, fed with the milestone's task summaries, deviations and follow-ups, written to M###-RETRO.md. Use after a milestone's last slice closed and reassess-roadmap ran, or when the user says retro, retrospective, what did we learn, lessons from this milestone. Not mid-milestone (reassess-roadmap) and not for closing a task (summarize-task).

193 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use plan-tune, ios-clean and 9 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • ShreyRaviSkill

    plan-tune

    Self-tuning question sensitivity + developer psychographic for gstack (v1: observational). Review which AskUserQuestion prompts fire across gstack skills, set per-question preferences (never-ask / always-ask / ask-only-for-one-way), inspect the dual-track profile (what you declared vs what your behavior suggests), and enable/disable question tuning. Conversational interface — no CLI syntax required.

    Also in 9 projects that use this

  • Saqlain-811Skill

    ios-clean

    Remove the DebugBridge SPM package and all #if DEBUG wiring from an iOS app. (gstack)

    Also in 5 projects that use this

  • Saqlain-811Skill

    ios-fix

    Autonomous iOS bug fixer. (gstack)

    Also in 5 projects that use this

  • seek888Skill

    pair-agent

    Pair a remote AI agent with your browser. One command generates a setup key and prints instructions the other agent can follow to connect. Works with OpenClaw, Hermes, Codex, Cursor, or any agent that can make HTTP requests. The remote agent gets its own tab with scoped access (read+write by default, admin on request). Use when asked to "pair agent", "connect agent", "share browser", "remote browser", "let another agent use my browser", or "give browser access". (gstack) Voice triggers (speech-to-text aliases): "pair agent", "connect agent", "share my browser", "remote browser access".

    Also in 11 projects that use this

  • ShreyRaviSkill

    landing-report

    Read-only queue dashboard for workspace-aware ship. Shows which VERSION slots are currently claimed by open PRs, which sibling Conductor workspaces have WIP work likely to ship soon, and what slot /ship would pick next. No mutations — just a snapshot. Use when asked to "landing report", "what's in the queue", "show me open PRs", or "which version do I claim next". (gstack)

    Also in 8 projects that use this

  • timurgaleevSkill

    document-generate

    Generate missing docs for a feature, module or project as tutorials, how-tos, reference and explanation.

    Also in 7 projects that use this

  • +1 more from Saqlain-811
  • +2 more from ShreyRavi

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 0 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 171 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If GSTACK_AVAILABLE is no (or unknown) or GSTACK_SKILL_OK is no: stop.

    line 76
  2. Very specific:

    If GSTACK_PIN_OK is no: continue, but say once that the installed gstack (GSTACK_VERSION) is older than the version ytstack was tested with.

    line 77
  3. Very specific:

    If BUN_OK is no: continue, but warn that gstack's helpers need bun >= 1.4.2 and may fail.

    line 78

“Common” is measured: kept by at least 6 in 10 of the 171 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

ytstack:retro

Thin wrapper around the installed gstack retro skill (~/.claude/skills/gstack/retro, ytstack tested against v1.96.0.0). Checks the install, invokes the gstack skill through the Skill tool, and writes the outcome as a ytstack artifact. gstack is the single source of truth for the procedure; ytstack owns only the precheck, the input (summaries) and the artifact.

ytstack context (resolved at render time)

# ytstack resolver (M016): checkout = where this shell runs, via the shared lib.
_LIB="${CLAUDE_SKILL_DIR}/../../hooks/lib/git-ctx.sh"
if [ -f "$_LIB" ]; then
  . "$_LIB"; yt_git_ctx "$PWD"; yt_resolve_yt_dir >/dev/null
  _PROJECT_DIR="$YT_TOPLEVEL"; _YT_DIR="$YT_DIR"; _YT_SCOPE="$YT_SCOPE"; _IS_GIT="$YT_IS_GIT"; _PROJECT_KEY="$YT_REPO_KEY"
else
  # Host did not substitute CLAUDE_SKILL_DIR (e.g. Codex adapter): project scope only.
  _IS_GIT=$([ "$(git rev-parse --is-inside-work-tree 2>/dev/null)" = true ] && echo yes || echo no)
  _PROJECT_DIR=$(git rev-parse --show-toplevel 2>/dev/null || pwd -P)
  _YT_DIR=""; _YT_SCOPE=none; _PROJECT_KEY=""
  [ -d "$_PROJECT_DIR/.ytstack" ] && { _YT_DIR="$_PROJECT_DIR/.ytstack"; _YT_SCOPE=project; }
fi
cd "$_PROJECT_DIR" 2>/dev/null || true
_PROJECT_SLUG=$(basename "$_PROJECT_DIR")
# gstack precheck (M017): installed dependency, not vendored
if command -v yt_gstack_ctx >/dev/null 2>&1; then
  yt_gstack_ctx >/dev/null
  echo "GSTACK_AVAILABLE: $YT_GSTACK_AVAILABLE"; echo "GSTACK_DIR: $YT_GSTACK_DIR"; echo "GSTACK_VERSION: ${YT_GSTACK_VERSION:-none}"
  echo "GSTACK_PIN_OK: $YT_GSTACK_PIN_OK (pin v$YT_GSTACK_PIN)"; echo "GSTACK_SKILL_OK: $(yt_gstack_skill_ok retro)"
  echo "BUN_OK: $YT_BUN_OK (${YT_BUN_VERSION:-none})"; echo "GSTACK_INSTALL_CMD: $YT_GSTACK_INSTALL_CMD"
else
  echo "GSTACK_AVAILABLE: unknown (shared lib not loaded)"
fi
# Milestone to review: the current one, or the newest with a done roadmap.
_M=none; _SUMMARIES=0; _RETRO_FILE=none
if [ -n "$_YT_DIR" ] && [ -f "$_YT_DIR/STATE.md" ]; then
  _M=$(sed -n 's/^current_milestone: *//p' "$_YT_DIR/STATE.md" | head -1)
  if [ "$_M" != none ]; then
    _SUMMARIES=$(ls "$_YT_DIR"/$_M-S[0-9][0-9]-T[0-9][0-9]-SUMMARY.md 2>/dev/null | grep -c .)
    _RETRO_FILE="$_YT_DIR/$_M-RETRO.md"
  fi
fi
echo "HAS_YTSTACK: $([ -n "$_YT_DIR" ] && echo yes || echo no)"
echo "MILESTONE: $_M"
echo "SUMMARIES: $_SUMMARIES"
echo "RETRO_FILE: $_RETRO_FILE"
echo "RETRO_EXISTS: $([ -f "$_RETRO_FILE" ] && echo yes || echo no)"

ytstack invocation notes

retro closes the loop that summarize-task opens: the milestone's M###-S##-T##-SUMMARY.md files (Outcome, Deviations, Follow-ups, Verification) are the raw material; the installed gstack retro skill runs the retrospective; ytstack keeps the result next to the milestone.

HARD-GATE: HAS_YTSTACK=no or MILESTONE=none: stop with "no milestone to review; run resume-session". SUMMARIES=0: stop with "the milestone has no task summaries yet; retro runs after the last summarize-task".

Before invoking gstack, read every summary of MILESTONE plus M###-CONTEXT.md (goal, exit criteria) and hand them to the gstack skill as the material under review. After it completes, write RETRO_FILE with frontmatter (milestone, project, created) and the gstack output; copy lessons that generalize into KNOWLEDGE.md and decisions into DECISIONS.md (one entry each, never silently).

Terminal State

Report RETRO_FILE and the number of KNOWLEDGE / DECISIONS entries added. Suggest ytstack:plan-milestone for the next milestone or ytstack:ship when the milestone is to be released. Do NOT auto-invoke any downstream skill.

HARD-GATE: gstack installed?

This wrapper runs the gstack retro skill that is installed on this machine (GSTACK_DIR above; ytstack is tested against gstack v1.96.0.0, bun >= 1.4.2). gstack is not vendored (DECISIONS 2026-11-07 "Vendor strategy").

  • If GSTACK_AVAILABLE is no (or unknown) or GSTACK_SKILL_OK is no: stop. Tell the user that ytstack:retro needs gstack and print the one-line install command from GSTACK_INSTALL_CMD. Do not improvise a retrospective from memory.
  • If GSTACK_PIN_OK is no: continue, but say once that the installed gstack (GSTACK_VERSION) is older than the version ytstack was tested with.
  • If BUN_OK is no: continue, but warn that gstack's helpers need bun >= 1.4.2 and may fail.

Procedure

  1. Invoke the Skill tool with retro (the installed gstack skill, not ytstack:retro), with the summaries and milestone context as its input. Follow it to completion.
  2. Apply the ytstack post-processing from "ytstack invocation notes" (RETRO_FILE, KNOWLEDGE / DECISIONS entries).
  3. Report per the Terminal State. Do NOT auto-invoke any downstream skill.

Checklist

You MUST create a TodoWrite task for each of these items:

  1. Run preamble -- resolver + gstack precheck + milestone summary count
  2. HARD-GATE -- stop with the install command when gstack is missing; stop without summaries
  3. Read the material -- every M###-S##-T##-SUMMARY.md + M###-CONTEXT.md
  4. Invoke installed retro via the Skill tool and follow it to completion
  5. Write M###-RETRO.md + KNOWLEDGE / DECISIONS entries
  6. Report + return -- paths + next-step suggestion, no auto-chaining

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.