Source

spm1001/trousse

25 skills · 373 combined installs

Skills from this source

#
Skill
Source
8W Activity
Installs
1
picture Generate images using Google Imagen. Use when user needs 'hero image', 'presentation visual', 'conceptual illustratio…
spm1001/trousse
57
2
server-checkup Systematic Linux server management. Use BEFORE making changes to capture baseline, then AFTER for verification. Trigg…
spm1001/trousse
49
3
diagram Orchestrates diagram creation with iterative render-and-check workflow. Invoke FIRST when asked to 'create a diagram'…
spm1001/trousse
40
4
screenshot Take screenshots to see what's on screen. Triggers on 'screenshot', 'grab a screenshot', 'have a look', 'can you see'…
spm1001/trousse
32
5
filing Orchestrates file cleanup with mandatory processing — reads content and extracts actions BEFORE moving files. Prevent…
spm1001/trousse
20
6
ia-presenter Writes and validates iA Presenter markdown where tab-indentation controls slide visibility. Triggers on 'presentation…
spm1001/trousse
17
7
titans Three-lens code review using parallel subagents: Epimetheus (hindsight — bugs, debt, fragility), Metis (craft — clari…
spm1001/trousse
17
8
setup Install behavioral skills from trousse. Use FIRST when onboarding a new machine or after fresh Claude Code install. C…
spm1001/trousse
16
9
github-cleanup Orchestrates cross-machine repo hygiene + GitHub account cleanup via an audit→approve→execute process that prevents a…
spm1001/trousse
15
10
google-devdocs Searches Google developer documentation via REST API — returns fresh Markdown from sites like cloud.google.com, fireb…
spm1001/trousse
15
11
review Code review alias. Invokes titans (three-lens review).
spm1001/trousse
15
12
skill-forge Orchestrates all skill development — required before writing or editing any SKILL.md file.
spm1001/trousse
15
13
sprite Controls InnerClaude instances on Sprites.dev VMs for testing workflows, install patterns, and Claude-to-Claude inter…
spm1001/trousse
13
14
amp-close Amp end-of-session ritual. Invoke FIRST when session is ending — 4-phase GODAR loop (gather context, orient via refle…
spm1001/trousse
12
15
close Orchestrates end-of-session capture via 5-phase GODAR framework — prevents work loss between sessions by surfacing le…
spm1001/trousse
12
16
open Re-orient to session context on demand. Loads companion skills (bon, todoist-gtd) based on what's present. Use when y…
spm1001/trousse
11
17
ardoise Spawns an isolated Claude with no CLAUDE.md, no skills, no hooks, no plugin context — only training weights and built…
spm1001/trousse
2
18
consomme BigQuery data analysis — BEFORE writing any BQ query, load this for methodology and dialect reference. Provides 5-sta…
spm1001/trousse
2
19
deglacer MANDATORY gate BEFORE running jq on any .jsonl under ~/.claude/ or reading past CC sessions. Invoke FIRST when intros…
spm1001/trousse
2
20
mandoline Transforms SPSS files, CSVs, and spreadsheet dumps into self-documenting BigQuery tables. Load BEFORE ingesting raw d…
spm1001/trousse
2
21
peer-review Spawn a peer Claude on the Anthropic conductor mesh to review code. The reviewer reads the target files, sends observ…
spm1001/trousse
2
22
scaffold Orchestrates new repo creation — required before setting up any batterie Python package. 5-step workflow (interview, …
spm1001/trousse
2
23
skill-check Quality gate for skill development and sharing. Validates naming, description quality, and structure. Before sharing,…
spm1001/trousse
2
24
toise Deep clean and structural health check for Claude-maintained codebases. INVOKE BEFORE adding significant complexity, …
spm1001/trousse
2
25
tamis Inspects which ad, martech, analytics, and affiliate tags fire on any website and identifies each by vendor — tag nam…
spm1001/trousse
1