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

Release Debrief

by sammcj in sammcj/agentic-coding

Summarises the delta between a tool's latest release and the last summary the user saw.

Apache-2.0Auto-check passedDevelopment

Install Release Debrief

skills CLI
$ npx skills add sammcj/agentic-coding --skill release-debrief -a claude-code

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

GitHub CLI
$ gh skill install sammcj/agentic-coding release-debrief --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/sammcj/agentic-coding.git skills-src && mkdir -p .claude/skills && cp -r skills-src/Skills/release-debrief .claude/skills/release-debrief && 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
release-debrief
GitHub stars
162
Token cost
~1.8k tokens
SKILL.md length
828 words
Files
6
Skills in repo
64
Repo updated
First seen
Licence
Apache-2.0

At a glance

Summarises the delta between a tool's latest release and the last summary the user saw.

  • Works in 7 steps: Load the tool profile. Read… → Read state. Load the tool's output file.… → Fetch the current changelog. Use… → …
  • The user asks about whats new
  • SKILL.md covers Supported Tools, Flow, Storage File Format and Scope Overrides, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Release Debrief is an agent skill from sammcj/agentic-coding. Summarises the delta between a tool's latest release and the last summary the user saw. Use when the user asks about what's new, the latest release, release notes, or the changelog of one of the supported tools: Claude Code, OpenCode, llama-swap, or llama.cpp.

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files (for example `resources/tools/claude-code.md`, `resources/tools/llama-cpp.md` and `resources/tools/llama-swap.md`).

It sits in Development, covering Changelog and release notes and LLM inference and serving. It works with llama.cpp. The repository describes itself as: Agentic Coding Rules, Templates etc... The licence is Apache-2.0.

When your agent uses it

  • The user asks about whats new
  • The latest release
  • The changelog of one of the supported tools: Claude Code

Example prompts

  • “Use the release-debrief skill to summarise the delta between a tool's latest release and the last summary the user saw”
  • “/release-debrief”

Requirements

  • Pre-approved tools (allowed-tools): Read, Write, Edit, Grep, Glob, WebFetch(domain:claude.com), WebFetch(domain:code.claude.com), WebFetch(domain:platform.claude.com), WebFetch(domain:opencode.ai), WebFetch(domain:github.com), WebFetch(domain:raw.githubusercontent.com), Bash(gh release list *), Bash(gh release view *), Bash(gh api *), Bash(open *)

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Load the tool profile. Read resources/tools/.md. It tells you where to fetch the changelog, how the version scheme works, which buckets to…
  2. Read state. Load the tool's output file. Parse last_seen_version from the frontmatter. If the file is missing, empty, or has no…
  3. Fetch the current changelog. Use WebFetch or ctx_fetch_and_index against the profile's Primary source. Pull Supporting sources only when…
  4. Identify the delta. Keep entries newer than the stored version, up to the latest release. Compare versions using the scheme in the profile
  5. Summarise. Group entries under the profile's Buckets. For each item
  6. Persist state. Use Edit (or Write if the output file doesn't yet exist) to update the tool's output file
  7. Output the full file path. After a successful write: "Debrief saved to: /absolute/path/to/resources/outputs/.md "

What it can do on your machine

Read from SKILL.md and the folder at commit 2f25ced. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Write
    • Edit
    • Grep
    • Glob
    • WebFetch(domain:claude.com)
    • WebFetch(domain:code.claude.com)
    • WebFetch(domain:platform.claude.com)
    • WebFetch(domain:opencode.ai)
    • WebFetch(domain:github.com)

    …and 5 more on the same allowed-tools line.

    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 markdown).

    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

Release Debrief loads about 1.8k tokens when it runs. Until then it costs about 69 tokens; SKILL.md has 828 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~69
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k

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 sammcj/agentic-coding at commit 2f25ced, republished under its Apache-2.0 licence (© sammcj). 828 words, ~1,796 tokens.

Download SKILL.mdSave it as .claude/skills/release-debrief/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
name
release-debrief
description
Summarises the delta between a tool's latest release and the last summary the user saw. Use when the user asks about what's new, the latest release, release notes, or the changelog of one of the supported tools: Claude Code, OpenCode, llama-swap, or llama.cpp.
allowed-tools
Read, Write, Edit, Grep, Glob, WebFetch(domain:claude.com), WebFetch(domain:code.claude.com), WebFetch(domain:platform.claude.com), WebFetch(domain:opencode.ai), WebFetch(domain:github.com), WebFetch(domain:raw.githubusercontent.com), Bash(gh release list *), Bash(gh release view *), Bash(gh api *), Bash(open *)
metadata.author
Sam McLeod (adapted from Arjen Schwarz)
disable-model-invocation
true
argument-hint
What's been the latest changes in llama.cpp since we last checked? Give me a debrief

Release Notes Catch-Up

Summarise what's changed in a supported tool since the user last ran this skill against it. No walkthroughs, no exercises. Focused digest of the delta.

Supported Tools

Each tool has a profile in resources/tools/<tool>.md (source URLs, buckets, gotchas) and an output file in resources/outputs/<tool>.md (last-seen version and summary history). Resolve both paths relative to this SKILL.md, not the user's current working directory.

ToolAliases the user may typeProfileOutput
Claude Codeclaude-code, claudecode, ccresources/tools/claude-code.mdresources/outputs/claude-code.md
OpenCodeopencode, open-coderesources/tools/opencode.mdresources/outputs/opencode.md
llama-swapllama-swap, llamaswapresources/tools/llama-swap.mdresources/outputs/llama-swap.md
llama.cppllama-cpp, llama.cpp, llamacppresources/tools/llama-cpp.mdresources/outputs/llama-cpp.md

Tool selection: match the tool from the user's prompt against the aliases above. If the user names something not in this table, reply with the supported list and stop.

Flow

  1. Load the tool profile. Read resources/tools/<tool>.md. It tells you where to fetch the changelog, how the version scheme works, which buckets to group under, what to drop, and what to watch out for. Treat the profile as authoritative for that tool.

  2. Read state. Load the tool's output file. Parse last_seen_version from the frontmatter. If the file is missing, empty, or has no frontmatter version, treat as a first run: summarise the last 3 releases per the profile's version scheme, without prompting.

  3. Fetch the current changelog. Use WebFetch or ctx_fetch_and_index against the profile's Primary source. Pull Supporting sources only when you need context for an entry (config schema comparison, API doc linking, editorial summary for colour). When the profile lists Conditional sources, test each condition against the delta once you have it and fetch the ones that hold - those carry buckets of their own.

  4. Identify the delta. Keep entries newer than the stored version, up to the latest release. Compare versions using the scheme in the profile:

    • semver - parse major.minor.patch and compare numerically per component.
    • build-number - strip any prefix (b, v) and compare as integer.
    • github-release-tag - use GitHub's release order (chronological).

    Never compare version tags as lexicographic strings.

  5. Summarise. Group entries under the profile's Buckets. For each item:

    • One line on what it is.
    • One line on why it matters or when you'd reach for it.
    • A doc link (from the profile's Feature Link Table, or the release page itself) when the feature is non-trivial.

    Apply the profile's Out of Scope list to drop low-signal entries. Apply the profile's Gotchas when deciding how to parse, group, or flag things. Keep tone dense and direct. Flag anything experimental, breaking, or schema-affecting prominently.

  6. Persist state. Use Edit (or Write if the output file doesn't yet exist) to update the tool's output file:

    • Set last_seen_version in the frontmatter to the latest version from the fetched changelog (the single newest one, even if the summary covers a range).
    • Set last_updated to today's date (ISO format).
    • Prepend a new ## <version> (<date>) section under # <Tool> Changelog Summaries containing the bucketed summary you just presented. When a single run covers multiple versions, use a range heading: ## <oldest> → <newest> (<date>).
    • Keep only the newest two ## sections. If adding the new section would leave three or more, remove the oldest so exactly two remain.

    Confirm in one line: Updated resources/outputs/<tool>.md to <version>. If the run fails or the user aborts before the summary is delivered, leave the file alone.

  7. Output the full file path. After a successful write: "Debrief saved to: /absolute/path/to/resources/outputs/<tool>.md "

Show full SKILL.md (273 more words)Show less

Storage File Format

Each output file follows this shape:

markdown
---
last_seen_version: 2.1.112
last_updated: 2026-04-17
---

# <Tool> Changelog Summaries

## <version> (<date>)

### <Bucket>
- ...

## <prior version> (<prior date>)

### <Bucket>
- ...

<version> in the heading can be a single version (2.1.112) or a range when one run covered several (2.1.109 → 2.1.112). last_seen_version in the frontmatter is always the single newest version. At most two ## sections: newest at top, prior run directly below. When prepending, drop the oldest.

Scope Overrides

  • Explicit version ("what's new since 2.1.90"): use the user's version instead of last_seen_version. Still persist state unless they say not to.
  • Date range ("everything in the last 2 weeks"): use changelog dates rather than version. Still persist state.
  • Area filter ("just hooks"): filter the delta to that area, but still persist state. Note the filter in the new section's heading: ## <version> (<date>, hooks only).
  • No persist ("don't update state"): skip step 6, tell the user state was not persisted.

Common Gotchas

  • Resolve resources/tools/<tool>.md and resources/outputs/<tool>.md relative to this SKILL.md. Users invoke the skill from arbitrary working directories.
  • Version parsing differs per tool - always read the profile's Version Scheme section before comparing. Don't assume semver.
  • If the stored version is newer than anything in the fetched changelog (user bumped it manually, or the source hasn't updated yet), say so plainly and don't invent a delta.
  • Use Edit to prepend the new section and remove the oldest so only two remain. Fall back to Write only when the file doesn't yet exist.
  • Don't mix tools in one output file. Each tool owns its own output file.
  • First-run heuristic (last 3 releases) applies per tool, not per invocation. If the user ran the skill on Claude Code yesterday and asks about OpenCode today, OpenCode is still a first run.

© sammcj, 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

SKILL.md and 5 other files in Skills/release-debrief of sammcj/agentic-coding.

  • SKILL.md
  • .gitignore
  • resources/tools/claude-code.md
  • resources/tools/llama-cpp.md
  • resources/tools/llama-swap.md
  • resources/tools/opencode.md

Open the folder on GitHubat commit 2f25ced

Compare with similar skills

Release Debrief 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.

Release Debrief compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Release Debrief this skillsammcj/agentic-coding162—~1.8kAutomated safety check: PassApache-2.0
Dev BumpNetis/heron102—~983Automated safety check: PassApache-2.0
Code ReviewJakeATX/llamAmpere149—~5.2kAutomated safety check: PassMIT
Aider DelegateamElnagdy/delegate-skills2.3k2 repos~3kAutomated safety check: PassMIT
Helmor Bump Vendorsdohooo/helmor1.3k—~2.1kAutomated safety check: PassApache-2.0
Qwen Mtp GgufR6410418/Jackrong-llm-finetuning-guide1.7k—~1.7kAutomated safety check: PassMIT

Similar skills

  • Dev Bump

    Netis/heron

    Bump Heron version via the VERSION-file SSOT. An agent skill from Netis/heron.

    102 GitHub stars~983 tokensUpdated 5 days ago
    AI & LLM EngineeringAuto-check passed

  • Code Review

    JakeATX/llamAmpere

    Review llama.cpp changes against project conventions and common reviewer pitfalls before a PR.

    149 GitHub stars~5.2k tokensUpdated 2 days ago
    AI & LLM EngineeringAuto-check passed

  • Aider Delegate

    amElnagdy/delegate-skills

    Delegate a coding task to Aider (aider) as a background implementer, then review its diff and land it yourself.

    2.3k GitHub starsUsed in 2 repos~3k tokens
    AI & LLM EngineeringAuto-check passed

  • Helmor Bump Vendors

    dohooo/helmor

    Bump or upgrade the pinned versions of Helmor's bundled agent CLIs, SDKs, and supporting binaries — Claude Code + claude-agent-sdk (lockstep), Codex, Cursor SDK, OpenCode, Kimi, Pi, and gh / glab /…

    1.3k GitHub stars~2.1k tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed

  • Qwen Mtp Gguf

    R6410418/Jackrong-llm-finetuning-guide

    Complete agent-ready workflow for Qwen-family MTP or nextn GGUF conversion and release.

    1.7k GitHub stars~1.7k tokensUpdated 3 mo ago
    AI & LLM EngineeringAuto-check passed

  • Quantization

    vllm-project/vllm-omni

    Work on vLLM-Omni quantization for diffusion, autoregressive, omni, or multi-stage models.

    7.1k GitHub stars~1.4k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

More from sammcj/agentic-coding

All 64 skills in this repo

  • Yue2 Music

    sammcj/agentic-coding

    A skill your agent uses when generating songs with YuE2, covering a recording via SheetSage2 audio-to-ABC, editing a score or lyrics with melody preservation, or building a reproducible listening…

    162 GitHub stars~2.3k tokensUpdated today
    Auto-check passed

  • Bento Slides

    sammcj/agentic-coding

    A skill your agent uses when creating or editing Bento (.bento.html) slide decks, including any request for a single-file HTML slide deck.

    162 GitHub stars~2.9k tokensUpdated today
    Auto-check passed

  • Idrive Backup

    sammcj/agentic-coding

    A skill your agent uses whenever the user wants you to manage, discuss or diagnose iDrive Backup configuration on macOS

    162 GitHub stars~1.7k tokensUpdated today
    Auto-check: notes

  • Piper Tts Training

    sammcj/agentic-coding

    Train custom TTS voices for Piper (ONNX format) using fine-tuning or from-scratch approaches.

    162 GitHub stars~1.4k tokensUpdated today
    Auto-check passed

  • PPTX To Md

    sammcj/agentic-coding

    Convert a PPTX slide deck into per-slide markdown that preserves both the verbatim text and the meaning of embedded screenshots, diagrams and charts in their original layout positions.

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

  • Skill Creator Primer

    sammcj/agentic-coding

    You MUST load this skill before the skill-creator skill AND before making ANY change to, or conducting a review of ANY Agent Skill.

    162 GitHub stars~9.8k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Release Debrief

What does Release Debrief do?

Summarises the delta between a tool's latest release and the last summary the user saw. Release Debrief is an agent skill from sammcj/agentic-coding. Summarises the delta between a tool's latest release and the last summary the user saw.

When should I use Release Debrief?

Release Debrief fits situations like: the user asks about whats new; the latest release; the changelog of one of the supported tools: Claude Code.

How do I install Release Debrief in Claude Code?

Run `npx skills add sammcj/agentic-coding --skill release-debrief -a claude-code`. Or copy the skill folder (Skills/release-debrief in sammcj/agentic-coding) into .claude/skills/release-debrief in your project. Claude Code loads it when a task matches its description.

How do I install Release Debrief in Codex?

Run `npx skills add sammcj/agentic-coding --skill release-debrief -a codex`. Or copy the skill folder (Skills/release-debrief in sammcj/agentic-coding) into .agents/skills/release-debrief in your project. Codex loads it when a task matches its description.

Can I use Release Debrief 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 sammcj/agentic-coding --skill release-debrief -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/release-debrief, .gemini/skills/release-debrief, .github/skills/release-debrief and .opencode/skills/release-debrief in your project.

What does Release Debrief need to run?

SKILL.md names no scripts, command-line tools or credentials: Release Debrief is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Write, Edit, Grep, Glob, WebFetch(domain:claude.com), WebFetch(domain:code.claude.com), WebFetch(domain:platform.claude.com), WebFetch(domain:opencode.ai), WebFetch(domain:github.com), WebFetch(domain:raw.githubusercontent.com), Bash(gh release list *), Bash(gh release view *), Bash(gh api *), Bash(open *).

Does Release Debrief 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 Release Debrief 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 Release Debrief use?

Release Debrief 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 Release Debrief use?

About 1.8k tokens (SKILL.md is roughly 7.2k 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 Release Debrief?

Skills that share tags, products or a category with Release Debrief: Dev Bump (Netis/heron, 102 stars), Code Review (JakeATX/llamAmpere, 149 stars), Aider Delegate (amElnagdy/delegate-skills, 2.3k stars) and Helmor Bump Vendors (dohooo/helmor, 1.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Release Debrief?

sammcj (a GitHub user) maintains it in sammcj/agentic-coding, which has 162 GitHub stars. The repository holds 64 skills in this directory. The repository was last updated on October 9, 2026.

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