capture-desktop
Capture a claude.ai Desktop session into the MEL file system. Use when Ane finishes a session in the Claude Desktop app and wants the work captured on the device — triggered by "/capture-desktop", "capture this desktop session", "I did this on Claude desktop", "save my desktop work", "import from claude.ai". Paste-driven; no cloud API exists. Stages a local transcript, classifies content into deliverables, decisions/rules, project-knowledge changes, and full log, then files each to its home. Auto-files transcript + deliverables; confirms memory/wiki/CLAUDE.md writes one-by-one.
- Installs
- 604
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/gasserane/personal-skills --skill capture-desktop- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads capture-desktop automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Capture Desktop Session
The device-side mirror of scripts/check_desktop_sync.py. That script governs
device-to-cloud sync. This skill governs cloud-to-device capture. claude.ai has
no API, so capture is paste-driven: Ane pastes a finished Desktop session and
this skill routes its content to the right places on disk.
Step 1 — Get the content
Ask Ane to paste the Desktop conversation, or accept a file path if she gives one. If the paste is long, write it to a temp file first to avoid truncation.
Step 2 — Stage the transcript
Run the helper to stage a verbatim, deduplicated transcript:
python scripts/capture_desktop.py stage --input <tempfile> --title "<short title>"
- Exit 0: prints the transcript path. Continue.
- Exit 3:
[DUP] already captured— this session was captured before. Tell Ane and stop unless she confirms she wants to re-route it anyway.
Transcripts are local-only (gitignored, OneDrive-backed). The staged transcript IS the "full log" bucket — no further action for that bucket.
Step 3 — Classify the content
Read the staged transcript. Sort its substantive content into four buckets:
- Deliverables — documents, analyses, tables, drafts Ane produced.
- Decisions / rules / lessons — locked decisions, framework calls, guidance
on how the system should work, feedback on your behaviour. Capture successes
as well as corrections: an approach the transcript shows Ane praised, reused,
or locked is a success worth banking as a
feedbackmemory (with Why: and How to apply:) so/improve-systemtrends confirmed successes, not only corrections. - Project-knowledge changes — edits that belong in canonical sources
(
mel_wiki/pages,~/.claude/CLAUDE.md). - Full log — already staged in Step 2. No action.
If a bucket is empty, say so. Do not invent content to fill it.
Step 4 — Route each bucket
Deliverables (auto-file). Propose a path under the work folder, save with the Write tool, and name it in the summary. Apply mel_wiki/wiki/concepts/edit-preservation-protocol.md when target file exists.
Decisions / rules / lessons (confirm each). For each item, propose the target — a memory file under the memory dir, a wiki entry, or a feedback memory — and show the exact content you will write. Get a yes/no from Ane before writing. Apply mel_wiki/wiki/concepts/edit-preservation-protocol.md when target file exists.
Project-knowledge changes (confirm each). For each item, propose the exact edit to the canonical source and get a yes/no. Apply the change with the Edit tool, scope-bounded. Apply mel_wiki/wiki/concepts/edit-preservation-protocol.md when target file exists.
- For
mel_wiki/edits: stage for the work-folder commit in Step 5. - For
~/.claude/CLAUDE.mdedits: after applying, commit cross-repo by runningbash ~/.claude-config-clone/scripts/sync-from-local.sh --auto "capture-desktop: <one-line reason>". This copies live CLAUDE.md into the claude-config clone, reconciles, commits, and pushes. It exits 0 silently if nothing changed.
Step 5 — Close the loop and commit
If any canonical source was edited (wiki or CLAUDE.md), run the sync check so the re-upload flag for the Desktop project fires:
python scripts/check_desktop_sync.py
Report any [DRIFT] it surfaces. Then commit the work-folder changes (deliverables
and mel_wiki/ edits only — transcripts are gitignored). Stage by name, never
git add -A:
git add <deliverable paths> <mel_wiki paths>
git commit -m "feat(capture): desktop session <slug> — <what landed>"
git push
Step 6 — Report
Deliver a tight summary:
CAPTURE-DESKTOP — <date>
Transcript: desktop-captures/<slug>/transcript.md (local)
Deliverables: <list or none>
Decisions/rules written: <list or none>
Canonical edits: <list or none> (CLAUDE.md pushed to claude-config: yes/no)
Sync check: <in sync / N drift flagged>
Commit: <short-SHA> pushed / nothing to commit
FAQ
What does the capture-desktop skill do?
Capture a claude.ai Desktop session into the MEL file system. Use when Ane finishes a session in the Claude Desktop app and wants the work captured on the device — triggered by "/capture-desktop", "capture this desktop session", "I did this on Claude desktop", "save my desktop work", "import from claude.ai". Paste-driven; no cloud API exists. Stages a local transcript, classifies content into deliverables, decisions/rules, project-knowledge changes, and full log, then files each to its home. Auto-files transcript + deliverables; confirms memory/wiki/CLAUDE.md writes one-by-one.
How do I install capture-desktop?
Run npx skills add https://github.com/gasserane/personal-skills --skill capture-desktop in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/capture-desktop/ (personal) or .claude/skills/capture-desktop/ (project).
Which AI agents can use capture-desktop?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is capture-desktop safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains capture-desktop?
It is published by gasserane in gasserane/personal-skills. It has 604 recorded installs.
More from gasserane/personal-skills
journal-reflection
gasserane/personal-skills
Guide Ane through structured reflection at end of day, end of week, after a decision, or after new learning material, producing Obsidian-compatible markdown and writing to the vault journal when the path is reachable. Use on 'journal', 'reflect on today', 'weekly review', 'after-action review', or asks that reference writing to the Obsidian vault. For a quick 4-line post-deliverable capture use /learned instead.
evidence-synthesis
gasserane/personal-skills
Conduct a rigorous rapid evidence assessment or systematic-lite literature review for MEL/SRHR questions. Use when Ane asks for "evidence review", "literature review", "evidence synthesis", "REA", "what does the evidence say", "what do we know about", or similar. Produces a structured brief with question framing, method, findings by theme, confidence grading, and implications for programme or evaluation design. Does not invent citations.
daily-brief
gasserane/personal-skills
Produce a scannable morning briefing for Ane (Senior MEL/SRHR Specialist at IPPF). Use when the user asks for "daily brief", "morning briefing", "start of day", "what's on today", "plan my day", or similar. Assembles today's priority, calendar, overdue items, pending decisions, and an energy check. Operates on user-provided inputs by default; richer when calendar/email MCP servers are connected.
decision-memo
gasserane/personal-skills
Draft a structured decision memo for Ane. Use when the user asks for a "decision memo", "decision doc", "options paper", "recommendation brief", or equivalent. Produces a scannable document with context, options, recommendation, risks, and reversibility. Applies Ane's CLAUDE.md writing style automatically.
video-content-analysis
gasserane/personal-skills
Convert FGD/webinar/SBCC video files into a structured artefact pack (transcript, frames, manifest, Tier 1 BLUF summary) the existing MEL specialists can consume. Use when Ane asks to "analyse a video", "transcribe a focus group", "process a webinar recording", "summarise a meeting recording", or runs /analyze-video . Tiered transcription (local Whisper for sensitive; M365 Stream for internal/public). Privacy + consent validated by construction. Per-run feedback prompt feeds the self-improvement loop.
power-bi-build
gasserane/personal-skills
Build IPPF-branded Power BI artefacts from analytical input. Use when Ane asks to build, scaffold, or update a Power BI dashboard, semantic model, DAX measures, or .pbip project. Applies IPPF Visual Identity 2025 brand, MEL-standard DAX measures, and three standard page recipes (indicator dashboard, equity disaggregation, methodology card). Requires the pbi CLI (pbi-cli-tool, command name pbi) installed and Power BI Desktop running with a .pbip open.
Popular backend & apis skills
find-skills
vercel-labs/skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
entra-app-registration
microsoft/azure-skills
Guides Microsoft Entra ID app registration, OAuth 2.0 authentication, and MSAL integration. USE FOR: create app registration, register Azure AD app, configure OAuth, set up authentication, add API permissions, generate service principal, MSAL example, console app auth, Entra ID setup, Azure AD authentication. DO NOT USE FOR: Key Vault secrets (use azure-keyvault-expiration-audit), general Azure resource security guidance.
google-agents-cli-adk-code
google/agents-cli
This skill should be used when the user wants to "write agent code", "build an agent with ADK", "add a tool", "create a callback", "define an agent", "use state management" — in a project that needs ADK (Agent Development Kit) API patterns and code examples. It provides a quick reference for agent types, tool definitions, orchestration patterns, callbacks, state management, the graph Workflow API, and reference recipes to study. Do NOT use for scaffolding (use google-agents-cli-scaffold) or deployment (use google-agents-cli-deploy).
embedded-captions
heygen-com/hyperframes
Add captions or subtitles to an existing single-subject talking-head video without editing the footage. Use for plain verbatim captions, cinematic captions embedded behind the subject, VFX captions, “炸/特效/酷炫字幕,” or a named identity from the 35-style catalog. Route by visual identity, not by backend engine. The quiet anchor rail is the default; embed every word only when the user explicitly wants a fully cinematic treatment. The workflow runs locally end to end, including transcription and subject matting; split multi-shot footage before applying it.
entra-agent-id
microsoft/azure-skills
Provision Microsoft Entra Agent Identity Blueprints, BlueprintPrincipals, and per-instance Agent Identities via Microsoft Graph, and configure OAuth 2.0 token exchange (fmipath, OBO, cross-tenant) including the Microsoft Entra SDK for AgentID sidecar. USE FOR: Agent Identity Blueprint, BlueprintPrincipal, agent OAuth, fmipath token exchange, agent OBO, Workload Identity Federation for agents, polyglot agent auth, Microsoft.Identity.Web.AgentIdentities. DO NOT USE FOR: standard Entra app registration (use entra-app-registration), Microsoft Foundry agent authoring (use microsoft-foundry).
neon
neondatabase/agent-skills
Overview of Neon, a complete set of cloud backend primitives around Lakebase Postgres: Auth, Object Storage, Functions, the AI Gateway, and Realtime. Start here to choose Neon for undecided login, files, APIs, and LLM calls, set up the CLI or MCP server, and follow the branch-first workflow. Use when building an app or backend on Neon, or when "Neon" or "Lakebase Postgres" is mentioned. Child skill neon-postgres wins for an existing DATABASEURL, SQL, schema, inspect, or search. Child skill neon-auth wins for login, users, sessions, identity routing, and Managed Better Auth setup. Child skill neon-realtime wins for live queries in reactive apps and agents. Also use for object storage, S3, buckets, serverless functions, function triggers, cron, AI gateway, LLM calls, realtime, logs, Loki, Grafana, observability, postgres, database, backend, Claimable Neon, neon.new, or a no-signup database.