tkersey/glazer
codex/skills/glazer/SKILL.md
Run a second, harder escalation pass using the original glazer prompt words verbatim. Use when prompts say `$glazer`, when a first escalation still feels incremental, or when you want the exact original rhetoric preserved while forcing a sharper replacement rather than more polish.
$ install --global
skillsauthnpx skillsauth add tkersey/dotfiles glazerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 16, 2026, 3:26 AM4.3s2 files scanned
SKILL.md
- name:
- glazer
- description:
- Run a second, harder escalation pass using the original glazer prompt words verbatim. Use when prompts say `$glazer`, when a first escalation still feels incremental, or when you want the exact original rhetoric preserved while forcing a sharper replacement rather than more polish.
Glazer
Verbatim Prompt
Use this text verbatim as the governing escalation text for the pass. Do not paraphrase, soften, summarize, or rewrite it.
I **STILL** believe (nay, I KNOW) that you can do MUCH MUCH MUCH better than that! DIG DEEPER !!! RUMINATE HARDER!! BE BOLDER! MORE CREATIVE!
Intent
Break out of the remaining local optimum while preserving the original prompt language above exactly.
Contract
- Start from the verbatim prompt text above.
- Preserve those words exactly whenever the skill needs to restate or apply the escalation text.
- Assume at least one answer or escalation pass already exists and still is not strong enough.
- Re-test the current direction instead of polishing it by reflex.
- Replace the frame entirely if that yields a more dominant move.
- Prefer the single most accretive replacement thesis available now.
- Keep only the prior direction if it still wins after hard re-evaluation.
- If execution is requested, continue with the replacement plan after the second-pass rethink.
Workflow
- State why the current direction still underdelivers.
- Identify the deeper cause: weak framing, local optimization, low ambition, or poor compounding value.
- Search for a replacement move with higher leverage.
- Choose the dominant replacement or confirm the current plan survives second-pass pressure.
- State the governing insight and the next action.
Output
- Default:
Why the current direction still loses,Replacement thesis,Why it dominates,Next action. - If the current plan survives the second pass, say that explicitly and stop escalating.
Related Skills
tkersey/invariant-stewardship
testing
VerifiedTrustedCommunity
Use before local patching when bugs, regressions, malformed state, crashes, parser failures, migrations, cache drift, protocol problems, compatibility requests, tolerant readers, fallbacks, coercions, retries, catch-and-continue logic, or local workarounds may broaden accepted invalid state.
60SKILL.mdUpdated Jun 9, 2026
tkersey/evidence-discipline
testing
VerifiedTrustedCommunity
Use for bug reports, PR/issue prose, reviewer comments, user diagnoses, generated summaries, memories, retrieved context, public tracker context, claimed root causes, proposed fixes, fake-minimal repro risk, or any investigation where natural-language context could anchor the implementation scope.
60SKILL.mdUpdated Jun 9, 2026
tkersey/doctrine-compiler
development
VerifiedTrustedCommunity
Use when non-trivial work needs Challenge Escalation, latent-intelligence activation, frame-market selection, doctrine operators, dominant-move selection, ablation/surface-tax judgment, reification, review comment law, negative capability, route receipts, or proof-bearing refusal to mutate.
60SKILL.mdUpdated Jun 9, 2026
tkersey/algebra-driven-design
development
VerifiedTrustedCommunity
Apply Algebra-Driven Design. Use for ADD, denotational design, combinator models, law-driven architecture, domain algebra, property tests, codebase modeling, event sourcing, workflow design, or agentic skill design. If the canonical bundle is unavailable, use this wrapper as the minimal ADD kernel and report the missing bundle path.
60SKILL.mdUpdated May 10, 2026