Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Session Retro

ASecurity

Propose one to three durable improvements to the shared agent toolset after meaningful work, including skill triggers, workflow gotchas, canonical instructions, parity gaps, and stale memory. Use when the user requests a retro, when a skill failed to trigger, after a notable workflow discovery, or at a genuine successful stopping point. Propose first and never edit without confirmation; unattended runs write proposals for later review.

2 stars
0 votes
0 copies
0 views
Added 9/22/2026
ai-agentsgo

Security Analysis

A100/100

Scanned 9/22/2026

Install to Claude Code

$npx -y skills add jckeen/dotfiles --skill session-retro --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Session Retro?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Session Retro
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/jckeen-session-retro/badge)](https://www.skillsdirectory.com/skills/jckeen-session-retro)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: session-retro
description: Propose one to three durable improvements to the shared agent toolset after meaningful work, including skill triggers, workflow gotchas, canonical instructions, parity gaps, and stale memory. Use when the user requests a retro, when a skill failed to trigger, after a notable workflow discovery, or at a genuine successful stopping point. Propose first and never edit without confirmation; unattended runs write proposals for later review.
---

# Session Retro

Improve the toolset, not the session log. Route ordinary history to changelog or
handoff workflows.

## Select The Right Source

- Shared behavior across agents: `agents/canon/` and regenerate the produced
  global instruction files.
- Portable workflows: `agents/skills/`.
- Claude-only workflows: `claude/skills/`.
- Private preferences or machine context: the relevant private memory repo.
- Architectural policy: an ADR when the repository uses ADRs.

Do not edit generated `claude/CLAUDE.md`, `codex/AGENTS.md`, or
`antigravity/GEMINI.md` directly.

## Reflect And Propose

1. Scan the completed work for a missed skill trigger, recurring footgun,
   reusable pattern, stale workflow, cross-agent parity gap, or obsolete memory.
2. Verify each candidate against current files, commands, and behavior. Age
   alone is not evidence of staleness.
3. Pick at most three high-value findings.
4. For each, show the target source, a short before/after or diff sketch, and
   the evidence from this session that justifies it.
5. Apply nothing until the user confirms which proposals to take. Retiring or
   deleting a skill requires explicit confirmation.

If nothing is worth changing, say exactly that in one line and stop.

## Apply Confirmed Changes

Use `$skill-creator` for new or substantially revised skills. Tighten trigger
descriptions around the phrasing that actually failed. Update shared canonical
sources before tool-specific adapters, regenerate derived instructions, run
parity and skill validation checks, and commit only the confirmed files.

Classify refreshed memory as Keep, Update, Consolidate, Replace, or Delete.
Never silently rewrite memory whose referent moved or disappeared.

## Unattended Mode

When invoked from unattended orchestration, write proposals to
`~/.claude/retro-proposals/YYYY-MM-DD-<project>.md` and do not apply them. A
later interactive retro should surface pending proposals first and remove the
proposal file only after the user accepts or rejects it.

Attribution

jckeenjckeen
View sourceMore from jckeen →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →