Agent skill

After Action Review

by Ckokoski in Ckokoski/AuthorAgent

Structured post-goal reflection that extracts lessons, evaluates quality, and feeds the self-improvement loop

MITAuto-check passedProduct & Project Management

Install After Action Review

skills CLI
$ npx skills add Ckokoski/AuthorAgent --skill after-action-review -a claude-code

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

GitHub CLI
$ gh skill install Ckokoski/AuthorAgent after-action-review --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/Ckokoski/AuthorAgent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/core/after-action-review .claude/skills/after-action-review && 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
after-action-review
GitHub stars
124
Token cost
~1.6k tokens
SKILL.md length
338 words
Files
1
Skills in repo
23
Repo updated
First seen
Licence
MIT

At a glance

Structured post-goal reflection that extracts lessons, evaluates quality, and feeds the self-improvement loop

  • Works in 6 steps: Gather Context → Quality Assessment → What Went Well → …
  • Tasks that involve Retrospectives
  • SKILL.md covers When It Runs, The Review Process, Review Storage and Aggregate Reviews, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

After Action Review is an agent skill from Ckokoski/AuthorAgent. Structured post-goal reflection that extracts lessons, evaluates quality, and feeds the self-improvement loop

Its SKILL.md is about 1.6k 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 Product & Project Management, covering Retrospectives. The repository describes itself as: The Autonomous AI Writing Agent — a secure, author-focused AI for fiction and nonfiction authors (Planning, Revision, Promotion, and more). The licence is MIT.

When your agent uses it

  • Tasks that involve Retrospectives

Example prompts

  • “/after-action-review”

Workflow steps

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

  1. Gather Context
  2. Quality Assessment
  3. What Went Well
  4. What Needs Improvement
  5. Extract Lessons
  6. User Feedback Request

What it can do on your machine

Read from SKILL.md and the folder at commit 47e9570. 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 (its code samples are json).

    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

After Action Review loads about 1.6k tokens when it runs. Until then it costs about 32 tokens; SKILL.md has 338 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~32
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

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 Ckokoski/AuthorAgent at commit 47e9570, republished under its MIT licence (© Ckokoski). 338 words, ~1,627 tokens.

Download SKILL.mdSave it as .claude/skills/after-action-review/SKILL.md (or your agent's skills folder).
name
after-action-review
description
Structured post-goal reflection that extracts lessons, evaluates quality, and feeds the self-improvement loop
author
AuthorAgent
version
1.0.0
triggers
after action review, review goal, post mortem, what went well, what went wrong, retrospective, goal review, debrief
permissions
file:read, file:write

After-Action Review — Core Skill

A structured reflection process that runs after every completed goal. Extracts concrete lessons, evaluates output quality, identifies what worked and what didn't, and feeds everything into the self-improvement loop.

When It Runs

  • Automatically after any goal completes (all steps done)
  • On request when the user says "review goal" or "what went well"
  • Periodically as part of a weekly self-assessment (if autonomous mode is enabled)

The Review Process

Step 1: Gather Context

Collect all relevant data about the completed goal:

  • Goal title, type, description
  • Number of steps planned vs. actually executed
  • Time taken per step and total
  • AI providers used and their costs
  • Which skills were triggered
  • Any errors or retries that occurred
  • User feedback received during execution
Step 2: Quality Assessment

Rate the overall output on 5 dimensions:

After-Action Review: "Plan my time travel novel"
═══════════════════════════════════════════════════

Quality Assessment:
┌─────────────────────────────────┬───────┐
│ Completeness                    │ 9/10  │
│ Did we accomplish the goal?     │       │
├─────────────────────────────────┼───────┤
│ Quality                         │ 7/10  │
│ How good was the output?        │       │
├─────────────────────────────────┼───────┤
│ Efficiency                      │ 6/10  │
│ Did we use resources well?      │       │
├─────────────────────────────────┼───────┤
│ User Satisfaction               │ ?/10  │
│ (Awaiting user rating)          │       │
├─────────────────────────────────┼───────┤
│ Reusability                     │ 8/10  │
│ Can this approach work again?   │       │
└─────────────────────────────────┴───────┘

Overall Score: 7.5/10
Step 3: What Went Well

Identify and document successes:

✅ WHAT WENT WELL
─────────────────
1. Dynamic AI planning produced a coherent 7-step plan
   → The AI planner correctly identified this as a "planning" goal
   → Steps were logically ordered (premise → characters → world → outline)

2. Gemini handled planning steps efficiently at zero cost
   → All 4 planning steps used free-tier Gemini
   → Quality was sufficient for brainstorming/outlining

3. Character profiles were detailed and interconnected
   → AI naturally created relationships between characters
   → Motivations tied directly to the central conflict

4. User accepted the outline without major revisions
   → Strong signal that the structure was sound
Step 4: What Needs Improvement

Identify failures, inefficiencies, and areas for growth:

⚠️ WHAT NEEDS IMPROVEMENT
──────────────────────────
1. World-building step was too generic
   → Setting description lacked sensory specificity
   → Lesson: Add "include 3+ sensory details per location" to world-building prompts

2. Step 5 (review) was redundant with step 4 (outline)
   → Could have been combined into a single step
   → Lesson: For planning goals, combine review into the outline step

3. Total execution time: 8 minutes for 7 steps
   → Steps 2 and 3 could have run in parallel
   → Lesson: Character and world-building don't depend on each other — parallelize

4. Cost: $0.00 (all Gemini free tier)
   → Good for planning, but creative writing would need a better model
   → Lesson: Use Gemini for planning, switch to Claude/DeepSeek for prose
Step 5: Extract Lessons

Convert observations into structured lessons for the improvement log:

json
[
  {
    "category": "worldbuild",
    "lesson": "Always include 3+ sensory details (sight, sound, smell, touch, taste) per location description",
    "confidence": 0.75,
    "source": "after_action_review"
  },
  {
    "category": "task_execution",
    "lesson": "For planning goals, character profiles and world-building can run in parallel (no dependency)",
    "confidence": 0.8,
    "source": "after_action_review"
  },
  {
    "category": "task_execution",
    "lesson": "Combine 'review and refine' into the preceding step for planning goals to reduce redundancy",
    "confidence": 0.7,
    "source": "after_action_review"
  },
  {
    "category": "task_execution",
    "lesson": "Use Gemini free tier for planning/outlining tasks. Reserve Claude/DeepSeek for creative prose.",
    "confidence": 0.85,
    "source": "after_action_review"
  }
]
Step 6: User Feedback Request

Ask the user for their assessment:

📋 Goal Complete: "Plan my time travel novel"

I've completed my self-review. Quick questions:

1. Overall, how would you rate the output? (1-10)
2. What specifically did you like most?
3. What would you change for next time?

(Or just say "looks good" and I'll note that as positive feedback!)

Review Storage

Reviews are saved to workspace/memory/reviews/:

workspace/memory/reviews/
├── 2026-02-24-plan-time-travel-novel.md
├── 2026-02-24-research-medieval-weapons.md
└── 2026-02-25-write-chapter-1.md

Each review file contains the full structured assessment in Markdown format, readable by both humans and the AI.

Aggregate Reviews

Over time, reviews accumulate into patterns:

review performance this week

Shows:

  • Goals completed: 5
  • Average quality score: 7.8/10
  • Most common improvement area: "Prose specificity"
  • Lessons extracted: 12 (8 high confidence)
  • User satisfaction trend: Improving ↑

Integration with Self-Improvement

The After-Action Review feeds directly into the self-improvement loop:

  1. Lessons extracted here are written to improvement-log.jsonl
  2. Next time a similar goal runs, those lessons are injected into context
  3. The review itself checks whether previous lessons were applied
  4. Creates a measurable improvement trajectory over time

Commands

  • after action review — Run a review on the most recently completed goal
  • review goal [id] — Review a specific goal
  • review performance — Aggregate performance metrics
  • what went well — Quick summary of recent successes
  • what went wrong — Quick summary of recent failures
  • rate last goal [1-10] — Provide a user rating for the last goal

© Ckokoski, MIT. 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 skills/core/after-action-review of Ckokoski/AuthorAgent.

Open the folder on GitHubat commit 47e9570

Compare with similar skills

After Action Review 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.

After Action Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
After Action Review this skillCkokoski/AuthorAgent124—~1.6kAutomated safety check: PassMIT
Weekly Engineering Retrogarrytan/gstack136k—~2.4kAutomated safety check: PassMIT
Dough Execute Planterryyin/lizard2.5k—~4.3kAutomated safety check: PassCustom licence
Oral Paper SkillAdkid-Zephyr/oral-paper-skill357—~1.9kAutomated safety check: PassNone
Deck Retroasheshgoplani/agent-deck1.1k—~1.8kAutomated safety check: PassMIT
Dough Execution Retrospectiveterryyin/lizard2.5k—~4kAutomated safety check: PassCustom licence

Similar skills

  • Builds a weekly engineering retrospective from git history: commit counts, per-person contributions, work patterns and code quality numbers over a chosen window.

    136k GitHub stars~2.4k tokensUpdated today
    Product & Project ManagementAuto-check passed
  • 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…

    2.5k GitHub stars~4.3k tokensUpdated today
    Product & Project ManagementAuto-check passed
  • 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.

    357 GitHub stars~1.9k tokensUpdated 23 days ago
    Product & Project ManagementAuto-check passed
  • Deck Retro

    asheshgoplani/agent-deck

    Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs.

    1.1k GitHub stars~1.8k tokensUpdated yesterday
    Product & Project ManagementAuto-check passed
  • Reviews planned, completed planless quick, or quick-to-planned execution against original intent, aggregate commits, current whole-product architecture, and tests, including after cleanup.

    2.5k GitHub stars~4k tokensUpdated today
    Product & Project ManagementAuto-check passed
  • Criticism Self Criticism

    HughYau/qiushi-skill

    批评与自我批评:在工作完成、阶段验收、收到批评或同类错误反复出现时,对成果和过程做诚实、具体、基于事实的审视,输出可执行的改进项,并处理外来批评而不辩解。触发信号包括 review、复盘、审查、"帮我看看有没有问题"、"你确定吗";任务刚开始或只是单步查询时不触发。

    3.8k GitHub stars~423 tokensUpdated 10 days ago
    Product & Project ManagementAuto-check passed

More from Ckokoski/AuthorAgent

All 23 skills in this repo
  • Comp Title Finder

    Ckokoski/AuthorAgent

    Find and analyze comparable titles for query letters, marketing, and positioning strategy

    124 GitHub stars~1.4k tokensUpdated 3 mo ago
    Auto-check passed
  • Continuity Check

    Ckokoski/AuthorAgent

    Scan manuscript for inconsistencies in characters, timeline, settings, and names

    124 GitHub stars~1.5k tokensUpdated 3 mo ago
    Auto-check passed
  • Deep Voice Analysis

    Ckokoski/AuthorAgent

    Advanced 47-marker voice analysis engine — analyzes your writing to build a comprehensive Voice Profile for AuthorClaw

    124 GitHub stars~1.4k tokensUpdated 3 mo ago
    Auto-check passed
  • Dictation Cleanup

    Ckokoski/AuthorAgent

    Transform raw speech-to-text dictation into polished prose while preserving the author's natural voice

    124 GitHub stars~1.2k tokensUpdated 3 mo ago
    Auto-check passed
  • Error Recovery

    Ckokoski/AuthorAgent

    Intelligent error diagnosis, automatic recovery strategies, and prevention of recurring failures

    124 GitHub stars~1.7k tokensUpdated 3 mo ago
    Auto-check passed
  • First Chapter Hook

    Ckokoski/AuthorAgent

    Analyze and rewrite first chapters for maximum reader retention using genre-specific hook patterns

    124 GitHub stars~1.3k tokensUpdated 3 mo ago
    Auto-check passed

Questions about After Action Review

What does After Action Review do?

Structured post-goal reflection that extracts lessons, evaluates quality, and feeds the self-improvement loop. After Action Review is an agent skill from Ckokoski/AuthorAgent.

When should I use After Action Review?

After Action Review fits situations like: tasks that involve Retrospectives.

How do I install After Action Review in Claude Code?

Run `npx skills add Ckokoski/AuthorAgent --skill after-action-review -a claude-code`. Or copy the skill folder (skills/core/after-action-review in Ckokoski/AuthorAgent) into .claude/skills/after-action-review in your project. Claude Code loads it when a task matches its description.

How do I install After Action Review in Codex?

Run `npx skills add Ckokoski/AuthorAgent --skill after-action-review -a codex`. Or copy the skill folder (skills/core/after-action-review in Ckokoski/AuthorAgent) into .agents/skills/after-action-review in your project. Codex loads it when a task matches its description.

Can I use After Action Review 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 Ckokoski/AuthorAgent --skill after-action-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/after-action-review, .gemini/skills/after-action-review, .github/skills/after-action-review and .opencode/skills/after-action-review in your project.

What does After Action Review need to run?

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

Does After Action Review 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 After Action Review 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 After Action Review use?

After Action Review is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does After Action Review 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 After Action Review?

Skills that share tags, products or a category with After Action Review: Weekly Engineering Retro (garrytan/gstack, 136k stars), Dough Execute Plan (terryyin/lizard, 2.5k stars), Oral Paper Skill (Adkid-Zephyr/oral-paper-skill, 357 stars) and Deck Retro (asheshgoplani/agent-deck, 1.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains After Action Review?

Ckokoski (a GitHub user) maintains it in Ckokoski/AuthorAgent, which has 124 GitHub stars. The repository holds 23 skills in this directory. The repository was last updated on July 11, 2026.

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