scriptoriumadmin/claude-skills
1
0
Fork 0
mirror of https://github.com/alirezarezvani/claude-skills.git synced 2026-09-07 08:26:02 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
claude-skills/productivity/capture
History
Exact
Claude 7405298b4b
fix: resolve the actionable reported issues (#954, #949, #933, #931, #969, #968, #924, #885) 
- #954: strip non-spec source/attribution keys from all 39 plugin.json
  manifests so Claude Code's validator accepts them; metadata preserved in
  new .claude-plugin/authoring-notes.json sidecars; check_plugin_json.py now
  hard-fails manifests carrying those keys and sanity-checks the sidecar;
  CLAUDE.md ClawHub schema section updated to the new rule.
- #949: move the c-level-agents plugin out of c-level-advisor/ to a
  top-level directory so the two marketplace sources no longer overlap;
  updated marketplace.json source, homepage, descriptions, all
  cross-references, docs, harness manifest, mirror-tree symlinks/indexes,
  and rebased the moved files' relative links; domain counters trued up
  (18 -> 19 domains).
- #933: replace dead links to the gitignored maintainer-local megaprompts/
  tree with annotated plain-text references (44 files: SKILL.md, READMEs,
  agents, commands).
- #931: DynamoDB on-demand pricing updated to post-Nov-2024 rates
  ($0.625/M writes, $0.125/M strongly consistent reads).
- #969: skill_security_auditor.py and the three dossier scripts reconfigure
  stdout/stderr to UTF-8 (errors=replace) so legacy Windows codepages no
  longer crash at print time; PYTHONUTF8=1 documented.
- #968: Windows Notes section in INSTALLATION.md + README pointer for the
  core.symlinks mirror-tree checkout caveat.
- #924/#885 residuals: hook commands quote "${CLAUDE_PLUGIN_ROOT}" paths in
  all plugin hooks.json/settings.json (space-safe roots); removed the stale
  pre-rename status/review mirror symlinks and index entries left over from
  the memory-status/memory-review rename.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Qgc6RYXWJPr5oW9DHU7zR4
2026-08-21 05:47:37 +00:00
..
.claude-plugin fix: resolve the actionable reported issues (#954, #949, #933, #931, #969, #968, #924, #885) 2026-08-21 05:47:37 +00:00
agents fix: resolve the actionable reported issues (#954, #949, #933, #931, #969, #968, #924, #885) 2026-08-21 05:47:37 +00:00
commands fix: resolve the actionable reported issues (#954, #949, #933, #931, #969, #968, #924, #885) 2026-08-21 05:47:37 +00:00
skills/capture fix: resolve the actionable reported issues (#954, #949, #933, #931, #969, #968, #924, #885) 2026-08-21 05:47:37 +00:00
README.md fix: resolve the actionable reported issues (#954, #949, #933, #931, #969, #968, #924, #885) 2026-08-21 05:47:37 +00:00

README.md

capture

Brain-dump organizer. Catches an unstructured stream of mixed thoughts, tasks, and ideas and transforms it into a clean four-section actionable system with zero information loss.

What it does

When the user dumps (explicitly with phrases like "brain dump" / "let me get this out of my head", or implicitly by pasting a long unstructured block of mixed ideas), the skill:

  1. Captures everything (zero loss; trivial items go in)
  2. Asks at most ONE mid-organization clarifying question — only if a single item is genuinely ambiguous between task and project
  3. Returns four sections:
    • Projects & Ideas — clustered themes with embedded questions/decisions
    • Tasks — flat scannable action list
    • Connections — real workspace links (Glob/Grep verified — never fabricated)
    • How I Can Help — concrete offers with what + where
  4. Ends with a directive question: "Which of these should I tackle?"
  5. Waits for the user's pick before any further action.

When the dump is small (≤5 items, unrelated), the skill drops into a compressed output instead of forcing 4 sections.

Source spec

This skill is a Path-B direct conversion of megaprompts/05-capture-megaprompt.md (maintainer-local draft spec — gitignored, not in the public repo) (PR #657). The megaprompt is the canonical spec; this plugin is the working implementation. Drift between the two is a bug — re-grill with /cs:grill-with-docs if they diverge.

Plugin layout

File Role
skills/capture/SKILL.md The skill itself (Claude reads this when triggered)
skills/capture/scripts/workspace_inventory.py Glob+Grep helper for Section 3 — given a working dir + keyword list, returns a structured inventory of file matches + folder structure. Stdlib-only.
skills/capture/scripts/dump_classifier.py Regex-classify dump lines into task / decision / question / project-component. Heuristic, not authoritative.
skills/capture/scripts/complexity_estimator.py Count items in dump; recommend full 4-section vs compressed output format.
skills/capture/references/workspace_detection.md Context-specific detection tactics (CLI / web / MCP / inaccessible)
skills/capture/references/voice_preservation.md Concrete examples of corporate-speak anti-patterns
skills/capture/references/complexity_matching.md When to compress vs full 4-section, with worked examples
agents/cs-capture.md Capture-organizer persona (no-fabrication, voice-preservation enforcer)
commands/cs-capture.md /cs:capture <dump> slash command for explicit invocation

Quick start

# Run the workspace-inventory helper against this repo
python skills/capture/scripts/workspace_inventory.py --root . --keywords "skill,megaprompt,capture"

# Classify a dump file
python skills/capture/scripts/dump_classifier.py path/to/dump.txt

# Estimate output complexity
python skills/capture/scripts/complexity_estimator.py path/to/dump.txt

License

MIT.