mrbinnacle/skills

1

click-clirunner-env-none-deletes Click's CliRunner.invoke `env=` only overrides keys the dict names; an absent key is not deleted. Pass `{key: None}` …

mrbinnacle/skills

3

2

closure-mode-at-boundaries Closure-mode discipline at workflow boundaries. Use when a sprint, phase, or vertical slice locks clean, or when a mu…

mrbinnacle/skills

3

3

downstream-instruction-framing Framing discipline for artifacts instructing a downstream reader — handoffs, plans, ADRs, subagent prompts. Separates…

mrbinnacle/skills

3

4

git-pull-rebase-trap Use before `git pull` where `pull.rebase` may be `true`. `--no-ff` does NOT stop a rebase under `pull.rebase=true` (s…

mrbinnacle/skills

3

5

github-pages-deploy-verification Verify a GitHub Pages (or any CDN-fronted) deploy actually serves new content. Poll on a marker that did not exist pr…

mrbinnacle/skills

3

6

halt-as-deliverable When a pre-registration, pre-flight or sanity gate refuses to produce your deliverable, the catch is often worth more…

mrbinnacle/skills

3

7

im-down Use when you are ending a Claude Code work session and the next session must resume from a verified packet instead of…

mrbinnacle/skills

3

8

im-up Use when a fresh Claude Code session must resume from an im-down packet and verify repository state before any work b…

mrbinnacle/skills

3

9

mock-masked-stub-trap A test that patches a helper which is itself a production stub reports green on a branch that never ran. Use when rev…

mrbinnacle/skills

3

10

parallel-review-disposition-schema Use when dispatching parallel agents to verify/adjudicate findings — adversarial verify, security disposition, design…

mrbinnacle/skills

3

11

pretooluse-bash-guard-prose-false-positive A PreToolUse Bash guard reads the whole command string, so it blocks prose that only mentions what it forbids. Use wh…

mrbinnacle/skills

3

12

router-skill-predicate-gap A router rule can be live, healthy and match nothing anyone types: the pattern list omits the ordinary word, or a JSO…

mrbinnacle/skills

3

13

subagent-research-reliability Pre-dispatch, name the return channel — a subagent handback can be empty. Verify tool grants match the task. Post-ret…

mrbinnacle/skills

3

14

success-test-accepts-any-output A success check accepting any non-empty output passes on failure, because failure output is non-empty too. Use when a…

mrbinnacle/skills

3