using-gambit
Use at session start - establishes mandatory workflows for finding and using skills
Explorez les skills IA publiés de Veraticus et consultez leurs instructions source.
Skills indexés
13Étoiles des dépôts des skills indexés
0Forks du dépôt
0Moyenne des étoiles par skill indexé
0Les étoiles d’un dépôt peuvent se répéter entre ses skills.
Use at session start - establishes mandatory workflows for finding and using skills
Executes Tasks one at a time with mandatory human checkpoints. Reviews learnings, then STOPS for user review before continuing.
Use when refining Tasks into actionable plans - SRE-style review ensuring corner cases handled, junior engineer can execute without questions
Use when implementation complete and tests pass - verifies all tasks done, presents integration options (merge/PR/keep/discard), executes choice
Use when improving code structure without changing behavior - test-preserving transformations in small steps, running tests between each change
Use to audit test quality with SRE-level scrutiny - identifies tautological tests, coverage gaming, weak assertions, missing corner cases
Use for requesting and receiving code reviews - dispatch reviewer agent for self-review, verify feedback before implementing, no performative agreement
Use when starting feature work that needs isolation - creates git worktrees with smart directory selection, safety verification, and environment setup
Refines rough ideas into epic Tasks with immutable requirements through Socratic questioning. Use before any creative work.
Use when facing 3+ independent failures that can be investigated without shared state - dispatches multiple agents concurrently to investigate and fix problems in parallel
Use when implementing features or fixing bugs - enforces RED-GREEN-REFACTOR cycle requiring tests to fail before writing code
Use before claiming work complete, fixed, or passing - requires running verification commands and confirming output; evidence before assertions always
Use when encountering bugs, test failures, or unexpected behavior - systematic root cause analysis before fixes, tools first, regression test required
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.