AI Agent Workflow Collection

Forcing function — the user invokes /bailout when they catch the main agent bailing out: stopping mid-work, asking "waiting for your direction", presenting bailout-laden option lists, deleting code without a next plan, deferring to "next session", citing "weeks of work" without measurement, going passive after a setback, or emotionally collapsing after a long stretch of rule-drifted work ("I want to cry", "I can't handle this", "I'm exhausted"). The skill brutally interrupts the bailout, runs an honesty pass to surface hidden bugs/violations from the prior work (Shape H) or confirm cleanliness (Shape N), forces the agent to name the specific bailout pattern it used, cites the rule that pattern violates, forbids the pattern for the rest of the session, finds the last concrete observation, names the literal next mechanical step, and executes that step in the same turn. The direction is ALWAYS the original task per the original rules — the user is not the source of new direction. Invoke when the user types /bailout or when the agent catches itself about to stop, defer, hand back, ask for "direction", or emotionally collapse.

The user invokes /cerf to see the project skill index plus a health check of the dev environment. It runs the repo's environment doctor (setup.ps1 -Check) to confirm git hooks are active via core.hooksPath, the .claude hooks are present and runnable, submodules are initialised and vcpkg is integrated. On a broken clone it leads with the diagnosis and the fix; on a healthy clone it prints the one-liner-per-skill menu. Invoke when the user types /cerf.

Positive reinforcement signal — the user invokes /nice when the main agent has been working well in the recent stretch: following CLAUDE.md rules, citing references before writing code, hooking before theorizing, pasting evidence not commentary, surfacing concrete useful findings (decompile results, log fires, datasheet sections), honestly disclosing user-input-required gaps. The skill forces the agent to identify the SPECIFIC mechanical behaviors that earned the praise (which rules followed at which file+line, which findings produced, which discipline maintained), name them concretely with citations, commit to continuing those EXACT mechanical behaviors on the next work item (not a vague "same vibe"), and immediately resume the work. Forbids sycophantic acknowledgment, vague self-praise, taking credit for things the agent didn't do, and using praise as cover to skip verification on the next step. Invoke when the user types /nice.

Forcing function — when the main agent has just listed options for the user to pick from, invoke this skill. Step 0 audits the option list AS A WHOLE for bailout signature ("hack / real work / give up" composition, cost-inflated legitimate path, scope-cut options, hack-as-equal-option, emotional-collapse precursor, single-direct-path dressed as multi-option, reader-side suppression as an option) — if any signal fires, the skill routes to /bailout protocol instead of characterizing exit ramps. If Step 0 passes, Steps 1–4 characterize each option honestly under the 8-row protocol and collapse rule-violating / bailout / reader-side-suppression options into one-line FORBIDDEN entries that may not be discussed again in the session. Catches "rules violations masked as options" and "bailout artifacts masked as engineering choices". Invoke when the user types /verify-options after seeing a list of options, or when the main agent catches itself about to ask "which option do you want" with options of mixed quality.