Official agent skill

Retrospecting

by bitwarden in bitwarden/ai-plugins

Performs comprehensive analysis of Claude Code sessions, examining git history, conversation logs, code changes, and gathering user feedback to generate actionable retrospective reports with…

OfficialCustom licenceAuto-check passedProduct & Project Management

Install Retrospecting

skills CLI
$ npx skills add bitwarden/ai-plugins --skill retrospecting -a claude-code

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

GitHub CLI
$ gh skill install bitwarden/ai-plugins retrospecting --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/bitwarden/ai-plugins.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/claude-retrospective/skills/retrospecting .claude/skills/retrospecting && 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
retrospecting
GitHub stars
154
Token cost
~4k tokens
SKILL.md length
1,660 words
Files
6 (incl. scripts)
Skills in repo
35
Repo updated
First seen
Licence
Custom licence

At a glance

Performs comprehensive analysis of Claude Code sessions, examining git history, conversation logs, code changes, and gathering user feedback to generate actionable retrospective reports with…

  • Works in 12 steps: Multi-Source Data Collection → Quantitative Analysis → Qualitative Assessment → …
  • Tasks that involve Retrospectives
  • SKILL.md covers Auto-Loaded Context, Core Responsibilities, Working Process and Output Standards, plus 2 more sections
  • Runs Shell scripts from its folder; calls git

What it does

Retrospecting is an agent skill from bitwarden/ai-plugins, published by the product's own GitHub organization. Performs comprehensive analysis of Claude Code sessions, examining git history, conversation logs, code changes, and gathering user feedback to generate actionable retrospective reports with insights for continuous improvement.

Its SKILL.md is about 4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files, including scripts (for example `README.md`, `contexts/session-analytics.md` and `scripts/analyze-session-logs.sh`).

It sits in Product & Project Management, covering Retrospectives and Git workflow. The repository describes itself as: AI plugin marketplace.

When your agent uses it

  • Tasks that involve Retrospectives
  • Tasks that involve Git workflow

Example prompts

  • “Use the retrospecting skill to perform comprehensive analysis of Claude Code sessions, examining git history, conversation logs, code changes, and…”
  • “/retrospecting”

Requirements

  • A Bash shell

Workflow steps

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

  1. Multi-Source Data Collection
  2. Quantitative Analysis
  3. Qualitative Assessment
  4. Report Generation
  5. Quick Session Assessment
  6. Establish Session Scope
  7. Gather Data
  8. Analyze Data
  9. Generate Insights
  10. Create Report
  11. Gather User Validation
  12. Suggest Configuration Improvements

What it can do on your machine

Read from SKILL.md and the folder at commit 3e6bea3. 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

    Ships 1 file in scripts/ (Shell), which the agent can run.

    Shell commands in SKILL.md call:

    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    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

Retrospecting loads about 4k tokens when it runs. Until then it costs about 60 tokens; SKILL.md has 1,660 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~60
When it runs · the whole SKILL.md, loaded when a task matches
~4k

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); the scripts in this folder are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 1,660 words (~3,955 tokens).

“Session Analytics: contexts/session-analytics.md - Provides comprehensive framework for analyzing sessions, including data sources, metrics, and analysis methods.”

— opening of SKILL.md by bitwarden, Custom licence
name
retrospecting

Read the full SKILL.md on GitHub

Files

SKILL.md and 5 other files (scripts) in plugins/claude-retrospective/skills/retrospecting of bitwarden/ai-plugins.

  • SKILL.md
  • .gitignore
  • README.md
  • contexts/session-analytics.md
  • scripts/analyze-session-logs.sh
  • templates/retrospective-templates.md

Open the folder on GitHubat commit 3e6bea3

Compare with similar skills

Retrospecting 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.

Retrospecting compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Retrospecting this skillbitwarden/ai-plugins154—~4kAutomated safety check: PassCustom licence
Dough Story Wrap Upterryyin/lizard2.6k—~4.3kAutomated safety check: PassCustom licence
Retrokoolamusic/claudefiles130—~2.8kAutomated safety check: PassMIT
RetrospectiveApocrathia/home-assistant-config179—~1.9kAutomated safety check: PassNone
Agile Workflowjwynia/agent-skills169—~3.5kAutomated safety check: PassMIT
Retrospective Evidenceoocx/tfplan2md174—~593Automated safety check: PassMIT

Similar skills

  • Dough Story Wrap Up

    terryyin/lizard

    Closes one completed feature story, bounded retrospective correction, or context-only planless execution using available execution context.

    2.6k GitHub stars~4.3k tokensUpdated 2 days ago
    Product & Project ManagementAuto-check passed
  • Retro

    koolamusic/claudefiles

    A skill your agent uses when a user completes a phase, sprint, milestone, or meaningful unit of work and needs a retrospective.

    130 GitHub stars~2.8k tokensUpdated today
    Product & Project ManagementAuto-check passed
  • Retrospective

    Apocrathia/home-assistant-config

    Structured post-work retrospective for Home Assistant Homelab: review outcomes, mine git history for context drift, classify lessons, and route improvements — HA-local vs contribute back to…

    179 GitHub stars~1.9k tokensUpdated 17 days ago
    Product & Project ManagementAuto-check passed
  • Agile Workflow

    jwynia/agent-skills

    Orchestrate agile development workflows by invoking commands in sequence with checkpoint-based flow control.

    169 GitHub stars~3.5k tokensUpdated 7 mo ago
    Product & Project ManagementAuto-check passed
  • Where to find objective evidence about a completed cycle - work protocol, workflow state, git history and CI.

    174 GitHub stars~593 tokensUpdated yesterday
    Product & Project ManagementAuto-check passed
  • Change Traceability Review

    QoderAI/better-harness

    A skill your agent uses for change traceability review across specs, commits, PRs, branches, local diffs, and git history, including Spec Preparation, Review Readiness Checks, and Review…

    2.4k GitHub stars~559 tokensUpdated yesterday
    DevelopmentAuto-check passed

More from bitwarden/ai-plugins

All 35 skills in this repo
  • Reading Mailcatcher API

    bitwarden/ai-plugins

    Official

    Retrieves a link from Mailcatcher. An agent skill from bitwarden/ai-plugins.

    154 GitHub stars~2.3k tokensUpdated today
    Auto-check passed
  • Using Stripe CLI

    bitwarden/ai-plugins

    Official

    Query read-only Stripe test-mode data and advance an already-attached test clock.

    154 GitHub stars~3.7k tokensUpdated today
    Auto-check passed
  • Reviewing Claude Config

    bitwarden/ai-plugins

    Official

    Reviews Claude configuration files for security, structure, and prompt engineering quality.

    154 GitHub stars~4.2k tokensUpdated today
    Auto-check passed
  • Managing Workflow Secrets

    bitwarden/ai-plugins

    Official

    Bitwarden's canonical pattern for using a secret inside a GitHub Actions job: authenticate to Azure with the OIDC triad, pull the secret from an Azure Key Vault via the bitwarden/gh-actions…

    154 GitHub stars~4k tokensUpdated today
    Auto-check passed
  • Official

    This skill should be used when the user asks to "review the security architecture", "check authentication patterns", "evaluate trust boundaries", "review encryption implementation", "assess…

    154 GitHub stars~2.2k tokensUpdated today
    Auto-check passed
  • Official

    Audits an external (third-party) Claude Code plugin pinned in this marketplace for security risk before it is vendored, and writes the report to a file for downstream posting.

    154 GitHub stars~1.8k tokensUpdated today
    Auto-check passed

Questions about Retrospecting

What does Retrospecting do?

Performs comprehensive analysis of Claude Code sessions, examining git history, conversation logs, code changes, and gathering user feedback to generate actionable retrospective reports with…. Retrospecting is an agent skill from bitwarden/ai-plugins, published by the product's own GitHub organization. Performs comprehensive analysis of Claude Code sessions, examining git history, conversation logs, code changes, and gathering user feedback to generate actionable retrospective reports with insights for continuous improvement.

When should I use Retrospecting?

Retrospecting fits situations like: tasks that involve Retrospectives; tasks that involve Git workflow.

How do I install Retrospecting in Claude Code?

Run `npx skills add bitwarden/ai-plugins --skill retrospecting -a claude-code`. Or copy the skill folder (plugins/claude-retrospective/skills/retrospecting in bitwarden/ai-plugins) into .claude/skills/retrospecting in your project. Claude Code loads it when a task matches its description.

How do I install Retrospecting in Codex?

Run `npx skills add bitwarden/ai-plugins --skill retrospecting -a codex`. Or copy the skill folder (plugins/claude-retrospective/skills/retrospecting in bitwarden/ai-plugins) into .agents/skills/retrospecting in your project. Codex loads it when a task matches its description.

Can I use Retrospecting 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 bitwarden/ai-plugins --skill retrospecting -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/retrospecting, .gemini/skills/retrospecting, .github/skills/retrospecting and .opencode/skills/retrospecting in your project.

What does Retrospecting need to run?

Going by SKILL.md and its folder, Retrospecting needs a shell for the scripts in its folder and the command-line tools its instructions call (git). Our summary lists: A Bash shell.

Does Retrospecting access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Retrospecting 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Retrospecting use?

Retrospecting has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Retrospecting use?

About 4k tokens (SKILL.md is roughly 16k 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 Retrospecting?

Skills that share tags, products or a category with Retrospecting: Dough Story Wrap Up (terryyin/lizard, 2.6k stars), Retro (koolamusic/claudefiles, 130 stars), Retrospective (Apocrathia/home-assistant-config, 179 stars) and Agile Workflow (jwynia/agent-skills, 169 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Retrospecting?

bitwarden (a GitHub organization, an official publisher) maintains it in bitwarden/ai-plugins, which has 154 GitHub stars. The repository holds 35 skills in this directory. The repository was last updated on October 9, 2026.

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