Skip to content
Back to search

hermes-field-kit

Field-tested, open-source skills for Hermes Agent.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/asimons81--hermes-field-kit/badge.svg)](/listings/asimons81--hermes-field-kit)

HTML

<a href="/listings/asimons81--hermes-field-kit"><img src="/api/listings/asimons81--hermes-field-kit/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Install any published skill by its repository-qualified identifier:

hermes skills inspect asimons81/hermes-field-kit/hermes-stack-doctor
hermes skills install asimons81/hermes-field-kit/hermes-stack-doctor --yes

Replace `hermes-stack-doctor` with any name from the published-skills list. Start a new Hermes session after installation because discovery may be cached for the lifetime of an existing session.

See [Installation](docs/installation.md) for inspection, installation, update behavior, removal, manual installation, and platform paths.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 147 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. <p align="center">
  2. <img src="assets/hero.jpg" alt="Hermes Field Kit banner featuring Hermes with gold and purple lightning" width="100%">
  3. </p>
  4. # Hermes Field Kit
  5. [![Validate repository](https://github.com/asimons81/hermes-field-kit/actions/workflows/validate.yml/badge.svg)](https://github.com/asimons81/hermes-field-kit/actions/workflows/validate.yml)
  6. [![License](https://img.shields.io/badge/license-Apache--2.0-blue.svg)](LICENSE)
  7. [![X: @tonysimons_](https://img.shields.io/badge/X-%40tonysimons__-000000?logo=x&logoColor=white)](https://x.com/tonysimons_)
  8. **Field-tested, open-source skills for Hermes Agent.**
  9. **Tags:** `hermes-agent` · `hermes-ai` · `ai-agents` · `agent-skills` · `developer-tools` · `automation` · `open-source` · `tonysimons_`
  10. Hermes Field Kit is a curated collection of reusable workflows that have earned their place through real, repeated use. It is intentionally not a bulk skill dump. Experimental entries are explicitly marked while they accumulate the field evidence required for stable promotion.
  11. ## Current status
  12. **Version 1.0.1 is the current tagged release. The 1.1.0 release branch expands the working catalog to thirteen stable skills plus six experimental skills.**
  13. The catalog includes private-by-default analytics, source-locked writing, evidence discipline, session continuity, Hermes-native work decomposition, post-build review, and an operational Field Kit organized around:
  14. ```text
  15. inspect -> diagnose -> plan -> execute -> verify -> hand off
  16. ```
  17. The repository applies the same admission rule to every future stable skill.
  18. ## The admission rule
  19. A skill belongs in the stable catalog only when all three statements are true:
  20. 1. It solves a real task.
  21. 2. It has been used in an actual workflow.
  22. 3. Another person can reproduce the intended behavior from the repository.
  23. Generated filler, speculative prompts, thin wrappers, and untested skill bundles do not qualify. Experimental skills must have a concrete use case, explicit limitations, behavior tests, and a defined path to stable promotion.
  24. ## What every published skill must provide
  25. - A Hermes-compatible `SKILL.md`
  26. - Direct tap discovery under `skills/<skill-name>/`
  27. - Clear triggers and counter-triggers
  28. - Sanitized examples from realistic workflows
  29. - Behavior-oriented test cases
  30. - Known limitations and failure modes
  31. - Platform and tool requirements
  32. - Independent versioning
  33. - No embedded credentials, private data, or personal configuration
  34. See the [skill specification](docs/skill-specification.md) for the complete contract.
  35. ## Repository map
  36. ```text
  37. skills/<skill-name>/ Published tap-discoverable skills
  38. catalog.json Machine-readable index and category metadata
  39. templates/skill-template/ Nonfunctional authoring scaffold
  40. schemas/ Machine-readable catalog and test schemas
  41. scripts/validate.py Dependency-free repository validator
  42. scripts/validate_release_wave.py Published-skill and public-tree hardening validator
  43. tests/ Validator contract tests
  44. docs/ Installation, design, testing, and release policy
  45. .github/ Contribution forms, dependency updates, and CI
  46. ```
  47. ## Published skills
  48. - [`what-have-we-done-today`](skills/what-have-we-done-today/README.md) **experimental**: Scan today's sessions, kanban boards, and cron runs across all profile stores and write an append-friendly daily markdown recap.
  49. - [`dont-lie-to-me`](skills/dont-lie-to-me/README.md) **experimental**: Separate observation, sourced claims, user reports, inference, unknowns, and contradictions before strong factual or completion claims.
  50. - [`hermes-change-review`](skills/hermes-change-review/README.md) **experimental**: Review implementation independently for intent fidelity, repository quality, and actual verification evidence.
  51. - [`hermes-environment-migration`](skills/hermes-environment-migration/README.md): Safely migrate Hermes environments with staged archives, integrity manifests, secret separation, selective imports, verification, and rollback.
  52. - [`hermes-gateway-doctor`](skills/hermes-gateway-doctor/README.md): Diagnose gateway failures from process, adapter, credential-posture, log, delivery, and persistence evidence without automatic repair.
  53. - [`hermes-kanbanize`](skills/hermes-kanbanize/README.md) **experimental**: Turn settled conversation/spec context into a Hermes-native Kanban graph with acceptance criteria, blocking edges, a verified frontier, and execution gating.
  54. - [`hermes-profile-audit`](skills/hermes-profile-audit/README.md): Compare a profile's declared responsibilities with its actual tools, skills, persistence, access, and observed behavior without rewriting it.
  55. - [`hermes-session-handoff`](skills/hermes-session-handoff/README.md) **experimental**: Build a portable continuation packet with verified state, artifacts, blockers, re-verification needs, and an exact fresh-session prompt.
  56. - [`hermes-skill-audit`](skills/hermes-skill-audit/README.md): Audit global and profile-local skills for dependencies, frontmatter, usage integrity, cron references, duplicates, and upstream drift.
  57. - [`hermes-skill-consolidate`](skills/hermes-skill-consolidate/README.md) **experimental**: Safely consolidate or restructure overlapping skills with read-only planning, scope-bound approval, rollback snapshots, staged writes, and post-change verification.
  58. - [`hermes-stack-doctor`](skills/hermes-stack-doctor/README.md): Discover the installation architecture, delegate to focused evidence contracts, and report a GREEN, YELLOW, or RED stack verdict without repairs.
  59. - [`hermes-token-audit`](skills/hermes-token-audit/README.md): Audit token usage and cost with live schema discovery, aggregate-first privacy, and clear separation between estimates and provider billing.
  60. - [`hermes-update-doctor`](skills/hermes-update-doctor/README.md): Investigate update failures by separating remote drift, repository divergence, process locks, stale caches, partial installs, and runtime mismatches.
  61. - [`interview-me`](skills/interview-me/README.md): Ask one high-value question at a time, inspect available sources before questioning, and stop when more questions would not change the next action.
  62. - [`omarchy-theme-maker`](skills/omarchy-theme-maker/README.md): Derive a contrast-checked Omarchy theme palette from any image, install it as the theme background, and apply it with `omarchy theme set`.
  63. - [`oss-tool-trust-audit`](skills/oss-tool-trust-audit/README.md): Read source and release machinery, treat popularity as context rather than proof, and separate technical legitimacy from adoption fit.
  64. - [`pre-build-feature-audit`](skills/pre-build-feature-audit/README.md): Run a read-only duplicate check across source, history, branches, issues, pull requests, roadmaps, and contributor guidance.
  65. - [`repo-readiness-audit`](skills/repo-readiness-audit/README.md): Determine whether a Git repository is ready for development, release, handoff, or contribution using independent evidence from repository and collaboration surfaces.
  66. - [`x-analytics-import`](skills/x-analytics-import/README.md): Validate, normalize, import, and compare X Analytics CSV exports through a repeatable private-by-default workflow.
  67. - [`x-post-writer`](skills/x-post-writer/README.md): Draft, rewrite, and repurpose short-form X content with source fidelity, format routing, and claim verification.
  68. ## Design principles
  69. - **Field-tested over fashionable.**
  70. - **Trust over volume.**
  71. - **Process predictability over ornamental prose.**
  72. - **Precise routing pointers over vague skill descriptions.**
  73. - **Progressive disclosure over giant always-loaded instructions.**
  74. - **Single sources of truth over copied environment facts.**
  75. - **Reproducible behavior over promises of guaranteed outcomes.**
  76. - **Safe defaults over environment-specific shortcuts.**
  77. - **Tap compatibility over aesthetically tidy but undiscoverable nesting.**
  78. Read [Design Principles](docs/design-principles.md) for the reasoning behind these rules.
  79. ## Installing skills
  80. Install any published skill by its repository-qualified identifier:
  81. ```bash
  82. hermes skills inspect asimons81/hermes-field-kit/hermes-stack-doctor
  83. hermes skills install asimons81/hermes-field-kit/hermes-stack-doctor --yes
  84. ```
  85. Replace `hermes-stack-doctor` with any name from the published-skills list. Start a new Hermes session after installation because discovery may be cached for the lifetime of an existing session.
  86. See [Installation](docs/installation.md) for inspection, installation, update behavior, removal, manual installation, and platform paths.
  87. ## Validation
  88. ```bash
  89. python scripts/validate.py
  90. python -m unittest discover -s tests -v
  91. python scripts/validate_release_wave.py
  92. ```
  93. The repository validator checks tap layout, catalog agreement, frontmatter, behavior cases, supporting paths, JSON validity, and common secret patterns. The hardening validator runs contract tests for every published skill, runs bundle validators where supplied, parses every Python file, checks relative Markdown links, rejects generated artifacts, and scans the public tree for private or credential-bearing material.
  94. ## Contributing
  95. Start with [CONTRIBUTING.md](CONTRIBUTING.md). New skill proposals use the dedicated GitHub issue form and must include evidence of real use without exposing private information.
  96. ## Versioning and releases
  97. The repository and catalog use Semantic Versioning. Individual skills carry their own SemVer version in `SKILL.md`. No release tag will be created solely for the scaffold.
  98. See [Release Process](docs/release-process.md) and [Compatibility](docs/compatibility.md).
  99. ## Security
  100. Never submit API keys, session tokens, private analytics exports, customer data, unpublished credentials, or personal configuration. Report suspected exposure privately as described in [SECURITY.md](SECURITY.md).
  101. ## Relationship to Hermes Agent
  102. This is an independent community repository for skills compatible with [Hermes Agent](https://github.com/NousResearch/hermes-agent). It is not an official Nous Research repository and does not imply endorsement.
  103. ## License
  104. Apache License 2.0. See [LICENSE](LICENSE).

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.