edit-skillslisted

# Skills tool A skill earns its place only by stopping a mistake the model makes without it, in as few words as that takes. The enemy is the skill that restates behavior the model already has and hides the one rule that changes anything. The overcorrection is an order stripped of its reason, which the model obeys to the letter past where it ends. ## When to use - Creating a skill or an agent, changing one, or judging whether one has grown too long. - Not for a fix that happens once, a habit of one project, or a limit a regex can check: a commit, `CLAUDE.md` or the verifier holds those, because a skill exists for a call that needs judgment. ## The shape | Part | Contract | |---|---| | `description` | Trigger only: the moments it fires, then what it leaves alone. A workflow written into it replaces the body, because the model acts on the summary it already read. | | Opening | A single paragraph naming the principle, the enemy and the overcorrection. | | `## When to use` | Bullets naming the symptoms first, then each "not for" case. | | Process | Numbered steps, at most eight, taken in order until one matches; every step is a rule with its reason. | | `## Red flags` | Only in a skill the model is tempted to skip: a table from the tempting thought to what is actually true. | | `## References` | A table of each file and the moment to read it; nothing is loaded before the step that needs it. | | `## Judgment` | A ladder saying which rule wins when two conflict. | ## Form - A