New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Session Retro

by agglayer in agglayer/agglayer

Review the current conversation and propose structured improvements to skills, documentation, and agent rules.

Apache-2.0Auto-check passedAgent Workflows

Install Session Retro

skills CLI
$ npx skills add agglayer/agglayer --skill session-retro -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install agglayer/agglayer session-retro --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/agglayer/agglayer.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/meta-session-retro .claude/skills/session-retro && rm -rf skills-src

Use ~/.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/

Facts

Skill name
session-retro
GitHub stars
117
Token cost
~833 tokens
SKILL.md length
403 words
Files
1
Skills in repo
7
Repo updated
First seen
Licence
Apache-2.0

At a glance

Review the current conversation and propose structured improvements to skills, documentation, and agent rules.

  • Works in 4 steps: Audit → Approval gate → Apply mode → …
  • Tasks that involve Agent instruction files
  • SKILL.md covers Steps and Guidelines
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Session Retro is an agent skill from agglayer/agglayer. Review the current conversation and propose structured improvements to skills, documentation, and agent rules.

Its SKILL.md is about 830 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Agent instruction files. The repository describes itself as: Rust implementation of the Agglayer. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Agent instruction files

Example prompts

  • “/session-retro”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Audit
  2. Approval gate
  3. Apply mode
  4. Verify/report

What it can do on your machine

Read from SKILL.md and the folder at commit 77667ba. 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

Session Retro loads about 833 tokens when it runs. Until then it costs about 31 tokens; SKILL.md has 403 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~31
When it runs · the whole SKILL.md, loaded when a task matches
~833

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 agglayer/agglayer at commit 77667ba, republished under its Apache-2.0 licence (© agglayer). 403 words, ~833 tokens.

Download SKILL.mdSave it as .claude/skills/session-retro/SKILL.md (or your agent's skills folder).
name
session-retro
description
Review the current conversation and propose structured improvements to skills, documentation, and agent rules.
disable-model-invocation
true

Review the full conversation and identify actionable improvements to the project's AI agent configuration and documentation.

Never delegate this skill to a subagent. The retro requires full conversation context.

Steps

Step 1: Audit
  • Scan the session for:
    • Corrections: where you were corrected or redirected.
    • Repeated patterns: workflows or knowledge applied multiple times.
    • Failed approaches: dead ends that future sessions should avoid.
    • Discoveries: codebase knowledge, architectural insights, or debugging techniques learned during the session.
    • Missing context: information you had to look up that should have been readily available.
    • Costly research: topics where significant time or tokens were spent exploring the codebase or external sources. Propose adding results to docs/knowledge-base/ so future sessions start with the answer.
  • Every correction must produce at least one proposal. Re-scan the conversation to confirm none were missed.
  • Produce proposals only, each with: What, Why (evidence), Where (exact file), Risk.
  • Changes should follow the Guidelines
Step 2: Approval gate
  • Present every proposal to the user using the multi-choice question tool (one question, multiple: true). Each option label is the proposal ID + short title; each description is a one-sentence summary.
  • Every correction received during the session must produce at least one proposal. Do not silently drop corrections.
  • No edits before explicit approval.
Step 3: Apply mode
  • Apply only approved items, minimally.
  • No auto-commit; leave changes staged/unstaged per your normal flow.
Step 4: Verify/report
  • Run your repo verification policy and report exact commands + pass/fail.
Show full SKILL.md (168 more words)Show less

Guidelines

  • Prefer updating existing files over creating new ones.
  • Keep skills focused: one workflow per skill.
  • Keep docs factual and concise.
  • Do not add speculative content. Only propose changes backed by concrete conversation evidence.
  • Proposed text must match the target file's style and brevity. In particular, AGENTS.md changes must be minimal (one or two short lines per rule).
  • Use .agents/skills/ for all agent conventions, including background knowledge (with user-invocable: false).
Where to propose changes (priority order)
  1. Skills (.agents/skills/): new skills for recurring workflows, or refinements to existing skills.
  2. Human-readable docs (docs/knowledge-base): codebase knowledge, architecture guides, debugging playbooks, patterns. Anything useful to both humans and AI agents. Terms should be defined in docs/knowledge-base/glossary.md. Other topics should be organized into documents with relevant names. Closely related subjects should be grouped under subfolders with understandable names. When creating or updating a document, use markdown links to refer to the glossary.
  3. Always-on rules (AGENTS.md): behavioral refinements to the agent interaction model. Keep changes minimal; this file should stay concise.

© agglayer, 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

Just SKILL.md in .agents/skills/meta-session-retro of agglayer/agglayer.

Open the folder on GitHubat commit 77667ba

Compare with similar skills

Session 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.

Session Retro compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Session Retro this skillagglayer/agglayer117—~833Automated safety check: PassApache-2.0
Using Agent Skillsaddyosmani/agent-skills103k4 repos~2.4kAutomated safety check: PassMIT
Claude ReflectBayramAnnakov/claude-reflect1.7k2 repos~627Automated safety check: PassMIT
Writing For Agentsbestofjs/bestofjs3.1k19 repos~2.7kAutomated safety check: PassMIT
Neat-Freak Knowledge CloseoutKKKKhazix/khazix-skills21k—~1.9kAutomated safety check: PassMIT
Task Observerrebelytics/one-skill-to-rule-them-all3.2k1 repos~12kAutomated safety check: PassCC-BY-4.0

Similar skills

  • Using Agent Skills

    addyosmani/agent-skills

    Meta-skill for choosing which workflow skill fits the task at hand, plus always-on habits: surface assumptions, stop on confusion, push back, keep it simple and stay in scope.

    103k GitHub starsUsed in 4 repos~2.4k tokens
    Agent WorkflowsAuto-check passed

  • Claude Reflect

    BayramAnnakov/claude-reflect

    Self-learning system that captures corrections during sessions and reminds users to run /reflect to update CLAUDE.md.

    1.7k GitHub starsUsed in 2 repos~627 tokens
    Agent WorkflowsAuto-check passed

  • Writing For Agents

    bestofjs/bestofjs

    Writing documents for agents. An agent skill from bestofjs/bestofjs.

    3.1k GitHub starsUsed in 19 repos~2.7k tokens
    Agent WorkflowsAuto-check passed

  • Neat-Freak Knowledge Closeout

    KKKKhazix/khazix-skills

    Brings project docs, agent rule files, authorized memory and leftover workspace files back in line with what the code and runtime actually do at the end of a work session.

    21k GitHub stars~1.9k tokensUpdated 7 days ago
    Agent WorkflowsAuto-check passed

  • Task Observer

    rebelytics/one-skill-to-rule-them-all

    Monitors task execution for skill improvement opportunities.

    3.2k GitHub starsUsed in 1 repo~12k tokens
    Agent WorkflowsAuto-check passed

  • SkillOpt Sleep Cycle

    microsoft/SkillOpt

    Official

    Runs an on-demand or nightly sleep cycle that reviews past Claude Code sessions and proposes validated updates to CLAUDE.md and skills.

    18k GitHub stars~2.3k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

More from agglayer/agglayer

  • Tech E2E Tests

    agglayer/agglayer

    Architecture and agent rules for kurtosis-cdk E2E tests. An agent skill from agglayer/agglayer.

    117 GitHub stars~1.1k tokensUpdated yesterday
    Auto-check: notes

  • Verify

    agglayer/agglayer

    Mandatory before any commit or push. An agent skill from agglayer/agglayer.

    117 GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed

  • Commit

    agglayer/agglayer

    Create a git commit following project conventions. An agent skill from agglayer/agglayer.

    117 GitHub stars~385 tokensUpdated yesterday
    Auto-check passed

  • Docs Knowledge Base

    agglayer/agglayer

    Create or update docs/knowledge-base/ chapters in mdbook format for human-first technical documentation.

    117 GitHub stars~344 tokensUpdated yesterday
    Auto-check passed

  • Style Prose

    agglayer/agglayer

    Text formatting conventions for markdown and prose files. An agent skill from agglayer/agglayer.

    117 GitHub stars~319 tokensUpdated yesterday
    Auto-check passed

  • Create PR

    agglayer/agglayer

    Create a pull request following project conventions. An agent skill from agglayer/agglayer.

    117 GitHub stars~364 tokensUpdated yesterday
    Auto-check passed

Categories

Questions about Session Retro

What does Session Retro do?

Review the current conversation and propose structured improvements to skills, documentation, and agent rules. Session Retro is an agent skill from agglayer/agglayer. Review the current conversation and propose structured improvements to skills, documentation, and agent rules.

When should I use Session Retro?

Session Retro fits situations like: tasks that involve Agent instruction files.

How do I install Session Retro in Claude Code?

Run `npx skills add agglayer/agglayer --skill session-retro -a claude-code`. Or copy the skill folder (.agents/skills/meta-session-retro in agglayer/agglayer) into .claude/skills/session-retro in your project. Claude Code loads it when a task matches its description.

How do I install Session Retro in Codex?

Run `npx skills add agglayer/agglayer --skill session-retro -a codex`. Or copy the skill folder (.agents/skills/meta-session-retro in agglayer/agglayer) into .agents/skills/session-retro in your project. Codex loads it when a task matches its description.

Can I use Session 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 agglayer/agglayer --skill session-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/session-retro, .gemini/skills/session-retro, .github/skills/session-retro and .opencode/skills/session-retro in your project.

What does Session Retro need to run?

SKILL.md names no scripts, command-line tools or credentials: Session Retro is instructions for the agent only.

Does Session 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 Session 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 Session Retro use?

Session 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 Session Retro use?

About 833 tokens (SKILL.md is roughly 3.3k 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 Session Retro?

Skills that share tags, products or a category with Session Retro: Using Agent Skills (addyosmani/agent-skills, 103k stars), Claude Reflect (BayramAnnakov/claude-reflect, 1.7k stars), Writing For Agents (bestofjs/bestofjs, 3.1k stars) and Neat-Freak Knowledge Closeout (KKKKhazix/khazix-skills, 21k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Session Retro?

agglayer (a GitHub organization) maintains it in agglayer/agglayer, which has 117 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 7, 2026.

Source: agglayer/agglayer on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.