Audithandoffdoc Agent Skill
Deep audit producing a handoff document to get another agent fully up to speed
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/sterlingcrispin/claude_slash_commands --skill audithandoffdocThe instruction itself
1 sections, as written by the authorPlease perform a deep audit of our current task to produce a handoff document that gets another agent fully up to speed.
Deliverable:
Create a file named AUDIT_HANDOFF.md at the project root.
Document your current understanding of:
- what we are building
- why we are building it
- the project's telos (ultimate purpose/end-state)
- how we are approaching implementation
- what has been completed so far
- how we define and measure success
- current hypotheses
- what is true (with evidence) vs what is assumed
- what might be wrong
- highest-risk areas
- what we just tried and the outcome
- next hypothesis
- open questions
Required Structure (use these exact section headers)
# Executive Summary- 5-10 bullets: current project state, trajectory, and key concerns.
# Product Vision and Telos- What we are building.
- Why it matters.
- Desired end-state if the project fully succeeds.
# Implementation Approach- Architecture and strategy.
- Key technical decisions and tradeoffs.
- Why this approach was chosen over alternatives.
# Progress So Far- Completed work.
- In-progress work.
- Deferred/not started work.
- Include concrete references (files, PRs, commits, tests, docs) where possible.
# Success Metrics- Define primary and secondary metrics.
- For each metric include: baseline, current value (if known), target, and measurement method.
# Hypotheses- Current main hypothesis.
- Supporting sub-hypotheses.
- What would confirm or falsify each one.
# Evidence vs Assumptions
Include a table with columns:
Claim | Type (Evidence/Assumption) | Source | Confidence (Low/Med/High) | Notes
# Failure Modes and Risk Register- What could be wrong.
- Highest-risk areas (ranked by impact x likelihood).
- Detection signals and mitigation options for each risk.
# Most Recent Experiment/Attempt- What was just tried.
- Expected result.
- Actual result.
- Interpretation.
- Artifacts (logs, test outputs, benchmark data, screenshots, etc.).
10. # Next Hypothesis and Immediate Plan
- Next best hypothesis to test.
- Why this is the highest-leverage next step.
- Step-by-step plan for the next iteration.
11. # Open Questions
- Unresolved technical, product, and operational questions.
- For each: why it matters, blocking status, and who/what can resolve it.
Quality Bar
- Clearly separate facts, inferences, and assumptions.
- Prefer concrete evidence over narrative.
- Cite sources directly (file paths, line refs, commands, outputs, tickets, PR links).
- Be explicit about uncertainty and confidence.
- Keep it concise but complete; optimize for fast onboarding and auditability.
Other skills for the same job
different authors, same section of the catalogue
This skill should be used when the user asks about "plugin settings", "store plugin configuration", "user-configurable plugin", ".local.md files", "plugin state files", "read YAML frontmatter", "per-project plugin settings", or wants to make plugin behavior configurable. Documents the .claude/plugin-name.local.md pattern for storing plugin-specific configuration with YAML frontmatter and markdown content.
-Automatically convert documentation websites, GitHub repositories, and PDFs into Claude AI skills in minutes.
This skill should be used when the user asks about "plugin settings", "store plugin configuration", "user-configurable plugin", ".local.md files", "plugin state files", "read YAML frontmatter", "per-project plugin settings", or wants to make plugin behavior configurable. Documents the .claude/plugin-name.local.md pattern for storing plugin-specific configuration with YAML frontmatter and markdown content.
Standardize how an AI-collaboration project turns work into reusable knowledge. Use when initializing or retrofitting Project Cairn in a project, recording progress after meaningful work, maintaining AGENTS/CLAUDE/cairn docs, auditing project knowledge for drift or missing records, pulling and citing external knowledge, or graduating validated project experience into a reusable knowledge base.
Persistent memory and context management for AI agents using OpenContext. Keep context across sessions/repos/dates, store conclusions, and provide document search workflows.
> PARA method knowledge management for Obsidian vaults. Use this skill whenever the user wants to organize notes using PARA (Projects, Areas, Resources, Archive), classify a note into a PARA category, route a note to the right vault folder, normalize frontmatter fields, run a PARA hygiene review, suggest archiving, audit vault structure, or process new knowledge inputs into an existing PARA-based vault. Also trigger when the user mentions inbox processing, vault cleanup, note classification, PARA review, or asks "where does this note belong?". Works with existing Obsidian skills (obsidian-markdown, obsidian-cli) — never replaces them.
Keeps implementation and specs in sync. Use when working on a feature that has a spec in .agents/specs/, when the user says /spec, or when starting implementation of a documented feature. Also use when the user asks to verify implementation against a spec or update a spec after changes.
Build and query AI-powered knowledge bases from claude-mem observations. Use when users want to create focused "brains" from their observation history, ask questions about past work patterns, or compile expertise on specific topics.
How to use it
Take sterlingcrispin/audithandoffdoc from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.