Retro

Name: Retro
Author: netresearch

netresearch/retro-skill

16 installs
3 repo stars
Updated August 4, 2026
netresearch/retro-skill

Helps with ai & agent building tasks.

About

retro is a Claude Code skill for ai & agent building. It helps solo builders move faster with AI-assisted coding.

retro
AI & Agent Building
AI-coding skill

Retro by the numbers

16 all-time installs (skills.sh)
+2 installs in the week ending Aug 4, 2026 (Skillselion tracking)
Ranked #11,068 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
Data as of Aug 5, 2026 (Skillselion catalog sync)

npx skills add https://github.com/netresearch/retro-skill --skill retro

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

[![Listed on Skillselion](https://skillselion.com/badge/skills/netresearch/retro-skill/retro.svg)](https://skillselion.com/skills/netresearch/retro-skill/retro)

Installs	16
repo stars	★ 3
Last updated	August 4, 2026
Repository	netresearch/retro-skill ↗

What it does

Helps with ai & agent building tasks.

Files

SKILL.mdMarkdownGitHub ↗

Retro — LLM-driven Session Retrospection

One efficient LLM pass over a session (or the stored memory backlog) detects friction, classifies it into one of six destinations, and materializes approved learnings.

Core principle: No silent writes — every materialization needs explicit per-proposal approval.

Modes

Detail per mode in references/workflow.md; full pipeline + commands in commands/retro.md.

`/retro` — Sweep: the whole current session.
`/retro "<problem>"` — Spotlight: one described issue.
`/retro outcome [session-id|--since N]` — replay a past session by what

happened to its output (reverts, rejected PRs, follow-up fixes).

`/retro audit [--scope project|repo|skill]` — cross-session architectural

drift, not per-session friction.

`/retro promote` — inventory already-written local memory (all slugs) and

re-home each note upward (skill-update › project-rule › user-memory; never project-local memory), draining the source only after the upward write is verified. See references/promote-mode.md.

Auto — optional SessionEnd hook (hooks/session-end.json), off by default.

Pipeline (all modes)

1. Mechanical pre-pass — scripts/detect-mechanical.py (Promote substitutes scripts/scan-memory-inventory.py). 2. LLM enrichment — add inferential signals; filter false positives. 3. Cross-session enrichment (optional) — Coach events.sqlite or JSONL scan. 4. Discover skills — scripts/find-org-skills.py (installed + org catalogue); find the owning skill first. 5. Classify (classification-heuristic.md) to the broadest useful scope; never project-local memory. 6. Eval consultation — read a matched skill's evals/; propose a TDD stub. 7. Proposal generation — prose Why + How-to-apply, grouped, ≤10. 8. Approval — approve / edit / reject per proposal. 9. Materialize per destination; for Promote, drain the source last (verified). 10. Report.

Boundaries

Always: LLM is primary classifier. Patches go to source repos, never the cache. Per-private-repo confirmation. Conventional Commits. DCO sign-off (git commit -s). Preserve commit signing.

Ask first: skill-match ambiguity, auto-mode activation, private-repo targets, dirty-worktree fallback, any promotion that makes a private note team-visible.

Never: auto-merge, silent writes, bot attribution, skip hooks (--no-verify), patch the cache, hardcode a static skill list, rm a drained memory (tombstone).

References

File	Purpose
`references/friction-catalog.md`	All ~32 friction signals (Schichten A/B/C)
`references/destination-taxonomy.md`	The six destinations
`references/classification-heuristic.md`	Friction → destination mapping
`references/skill-discovery.md`	Finding skills at runtime
`references/patch-workflow.md`	Source-repo patching (never cache)
`references/eval-integration.md`	Evals for context and TDD stubs
`references/promote-mode.md`	Promote: scan, classify, materialize-then-drain
`references/workflow.md`	All modes + pipeline phase selection

version: 1
skill_id: retro

preconditions:
  - type: command
    pattern: "python3 --version"
    desc: "python3 available for mechanical pre-pass"

mechanical:
  - id: RT-01
    type: file_exists
    target: skills/retro/SKILL.md
    severity: error
    desc: "SKILL.md exists"

  - id: RT-02
    type: file_exists
    target: commands/retro.md
    severity: error
    desc: "/retro command definition exists"

  - id: RT-03
    type: file_exists
    target: scripts/detect-mechanical.py
    severity: error
    desc: "Mechanical pre-pass script exists"

  - id: RT-04
    type: command
    pattern: "python3 -m py_compile scripts/detect-mechanical.py"
    severity: error
    desc: "Mechanical pre-pass script is syntactically valid Python"

  - id: RT-05
    type: file_exists
    target: scripts/find-installed-skills.sh
    severity: error
    desc: "Skill discovery helper exists"

  - id: RT-07
    type: command
    pattern: "python3 -m unittest discover -s tests -q"
    severity: error
    desc: "Detector test suite passes (guards A1/A14 signal regressions)"

  - id: RT-06
    type: command
    pattern: "bash -n scripts/find-installed-skills.sh"
    severity: error
    desc: "Skill discovery script is syntactically valid bash"

  - id: RT-10
    type: file_exists
    target: "{references/friction-catalog.md,references/destination-taxonomy.md,references/classification-heuristic.md}"
    severity: error
    desc: "Core reference docs exist (catalog, taxonomy, heuristic)"

  - id: RT-11
    type: file_exists
    target: "{references/skill-discovery.md,references/patch-workflow.md,references/workflow.md}"
    severity: error
    desc: "Workflow reference docs exist (discovery, patch, workflow)"

  - id: RT-20
    type: file_exists
    target: hooks/session-end.json
    severity: warning
    desc: "Optional SessionEnd hook template provided"

  - id: RT-21
    type: command
    pattern: "jq -e . hooks/session-end.json > /dev/null"
    severity: error
    desc: "SessionEnd hook JSON is valid"

  - id: RT-30
    type: file_exists
    target: docs/specs/retro-skill.md
    severity: warning
    desc: "Spec mirror exists for traceability"

  - id: RT-40
    type: file_exists
    target: scripts/validate-evals.py
    severity: error
    desc: "Eval validator script exists"

  - id: RT-41
    type: command
    pattern: "python3 -m py_compile scripts/validate-evals.py"
    severity: error
    desc: "Eval validator script is syntactically valid Python"

  - id: RT-42
    type: command
    pattern: "python3 scripts/validate-evals.py"
    severity: error
    desc: "Retro's own eval scenarios are present (>=5) and well-formed (id/trigger/expected/negative_expected)"