coroboros/agent-skills / skills/humanize-en
humanize-en
VerifiedRemove AI writing tells from English prose while preserving meaning, structure, code, links and quotations. Use for humanize this, remove AI slop and polish the English on inline text or prose files. Optional -f BRAND-VOICE.md applies brand rules with explicit mechanical and semantic coverage. Inherit authorized rewrite scope; audit/propose remains read-only. Structural README work belongs to write-clear-readme.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 18.1 KB |
| eval-corpus/brand-voice/brand-allcaps-01.json | config | 1.2 KB |
| eval-corpus/brand-voice/brand-clean-01.json | config | 1.3 KB |
| eval-corpus/brand-voice/brand-lexicon-01.json | config | 911 B |
| eval-corpus/brand-voice/brand-pronouns-01.json | config | 978 B |
| eval-corpus/brand-voice/brand-rewrite-rules-01.json | config | 946 B |
| eval-corpus/brand-voice/brand-rhetoric-01.json | config | 1.1 KB |
| eval-corpus/samples/clean-prose-01.json | config | 417 B |
| eval-corpus/samples/docs-intro-01.json | config | 631 B |
| eval-corpus/samples/hero-landing-01.json | config | 637 B |
| eval-corpus/samples/release-notes-01.json | config | 571 B |
| evals/evals.json | config | 2.8 KB |
| references/output-formats.md | markdown | 1.7 KB |
| references/patterns.md | markdown | 18.3 KB |
| references/schemas.md | markdown | 10.7 KB |
| references/voice.md | markdown | 2.8 KB |
| scripts/__init__.py | script | 0 B |
| scripts/brand_prescan.py | script | 28.0 KB |
| scripts/eval_patterns.pyexecutable | script | 5.3 KB |
| scripts/prescan.pyexecutable | script | 11.0 KB |
| scripts/utils.py | script | 1.6 KB |
| scripts/validate.py | script | 7.0 KB |
references/output-formats.md
View on GitHub# Output formats
Canonical templates the skill emits depending on input mode and whether `-f <voice-doc>` is set. Every invocation closes with one of these — never improvise the structure.
## For inline text (default mode)
```
## Rewrite
<humanized text>
## Patterns removed
- #N <pattern name> — <short note, e.g., "4 instances, em-dashes converted to commas">
- ...
```
## For inline text under `-f`
```
## Rewrite
<humanized text>
## Coverage report
| Rule | Source | Detection | Hits | Action | Residual |
|---|---|---|---|---|---|
| #14 em-dash density | universal | prescan | 8 | preserved (citation format) | 0 |
| brand:all_caps_emphasis | brand | prescan-brand | 14 | rewrite | 0 |
| brand:negative_parallelism | brand | prescan-brand | 4 | rewrite | 0 |
| brand:forbidden_lexicon (26 entries) | brand | prescan-brand | 0 | n/a | 0 |
```
Every YAML rule appears in the table — even with 0 hits — so a future pass can verify the prior pass actually checked the rule. Missing rows are a hard failure, not a stylistic choice.
## For file paths
```
## Diff preview
<unified-diff-style or before/after blocks for changed passages>
## Coverage report
<as above; count-only summary in default mode>
## Validation report (under `-f` only)
status: clean | residuals | regression
<residual hits or regression diff if any>
<Applied diff for an authorized rewrite; proposed diff for audit-only.>
```
Carry the user's authorized target and mode through a parent skill invocation. Apply an explicitly requested rewrite without another approval prompt. Audit/propose stays read-only; a parent call or filepath alone cannot authorize a new edit. Label mechanical validation separately from semantic rule coverage.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |