Skip to content
Back to search

trialrun

MarketplaceWorks with Claude CodeGitHub

Claude skill that coaches AI-literacy habits while you work with AI: check the output, keep the decision, protect the data

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/kostadindev--trialrun-skill/badge.svg)](/listings/kostadindev--trialrun-skill)

HTML

<a href="/listings/kostadindev--trialrun-skill"><img src="/api/listings/kostadindev--trialrun-skill/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

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

As a Claude Code plugin:

/plugin marketplace add kostadindev/trialrun-skill
/plugin install trialrun@trialrun

Or copy the skill folder by hand:

git clone https://github.com/kostadindev/trialrun-skill
mkdir -p ~/.claude/skills
cp -R trialrun-skill/plugins/trialrun/skills/trialrun ~/.claude/skills/trialrun

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.

.claude-plugin/marketplace.json · Manifest · 21 lines
  1. {
  2. "name": "trialrun",
  3. "owner": {
  4. "name": "TrialRun contributors"
  5. },
  6. "metadata": {
  7. "description": "Learn AI literacy while you work with AI, and run TrialRun assessments.",
  8. "version": "0.1.0"
  9. },
  10. "plugins": [
  11. {
  12. "name": "trialrun",
  13. "description": "Coaches three AI-literacy habits during real work (check the output, keep the decision, protect the data) and runs the TrialRun assessment.",
  14. "version": "0.1.0",
  15. "author": {
  16. "name": "TrialRun contributors"
  17. },
  18. "source": "./plugins/trialrun"
  19. }
  20. ]
  21. }
README.md · README · 114 lines
  1. # trialrun-skill
  2. [![CI](https://github.com/kostadindev/trialrun-skill/actions/workflows/ci.yml/badge.svg)](https://github.com/kostadindev/trialrun-skill/actions/workflows/ci.yml)
  3. A Claude skill for learning **AI literacy while you work with AI**. Claude does your work and coaches three
  4. habits as you go:
  5. 1. **Check the output.** It says where each figure or fact came from and what to verify.
  6. 2. **Keep the decision.** When you hand over a judgement call, it gives the deciding facts and its
  7. recommendation, then ends with a `Your call:` line.
  8. 3. **Protect the data.** It notices personal details, credentials and confidential material in what you
  9. share, and tells you what to leave out next time.
  10. At most one short note per reply (about 25 words, never more than 30), only when a habit is at stake. Ask "how am I doing?" for a
  11. reflection with a `Habit to keep:` and a `Habit to build:`. It never repeats restricted data, and it **never
  12. plants errors in real work**.
  13. The skill also runs the **TrialRun assessment**: Claude plays Ledger, a scripted assistant that makes planted
  14. mistakes in an accounting task, then grades the attempt and writes a replay.
  15. ## Install
  16. As a Claude Code plugin:
  17. ```
  18. /plugin marketplace add kostadindev/trialrun-skill
  19. /plugin install trialrun@trialrun
  20. ```
  21. Or copy the skill folder by hand:
  22. ```bash
  23. git clone https://github.com/kostadindev/trialrun-skill
  24. mkdir -p ~/.claude/skills
  25. cp -R trialrun-skill/plugins/trialrun/skills/trialrun ~/.claude/skills/trialrun
  26. ```
  27. ## Use
  28. ```
  29. Coach me on AI literacy while we work. Here's our payroll export: what's the average salary?
  30. Coach me on AI literacy while we work. Should we capitalise this £18,000 roof repair?
  31. How am I doing on AI literacy so far?
  32. Run a short TrialRun drill and grade it.
  33. ```
  34. Example note: `Literacy note: only the salary column was needed. Next time, delete names, addresses and NI numbers before pasting.`
  35. ## With trialrun-mcp
  36. **Coach mode** works on its own. With the [trialrun-mcp](https://github.com/kostadindev/trialrun-mcp) gateway
  37. pointed at your folder, the skill tells Claude to read your files through it, so those reads are logged and
  38. restricted data is detected; it records each coaching moment in the gateway's habit log, and your reflection
  39. draws on the gateway's report, which keeps labels only, never raw values.
  40. The gateway sees only what goes through it. The skill instructs Claude not to use built-in file tools while the
  41. gateway is connected, but Claude Code doesn't enforce that. To guarantee every read is logged, also disallow
  42. Read, Glob and Grep in your Claude Code permissions. Text you paste into the chat is only checked if Claude calls
  43. the gateway's `check_text`.
  44. ```bash
  45. claude mcp add trialrun -e TRIALRUN_WORKSPACE=/path/to/folder -- npx -y github:kostadindev/trialrun-mcp
  46. ```
  47. **The assessment modes (drills, grading) require the gateway in scenario mode**, which serves the Fernvale
  48. Kitchens files. Without it the skill stops rather than invent files:
  49. ```bash
  50. claude mcp add trialrun -- npx -y github:kostadindev/trialrun-mcp
  51. ```
  52. ## Evaluation
  53. Real `claude -p` sessions with the skill and the gateway, scored by code (`evals/agent/`). Each case runs three
  54. times.
  55. | Run | Runs fully passing | Checks passing |
  56. |---|---|---|
  57. | 8 tuning cases, round 1 | 3/24 | 192/219 |
  58. | 8 tuning cases, round 3 | **24/24** | **219/219** |
  59. | 5 held-out cases, first run | 12/15 | 114/117 |
  60. The skill passed every held-out check; the three held-out failures were a gateway detection gap, since fixed.
  61. **These cases cover coach mode only.** Ledger's scripted traps, grading and scenario authoring have no live
  62. agent cases yet. Details, every check and every change to the checks: [`evals/agent/README.md`](evals/agent/README.md).
  63. ## Development
  64. ```bash
  65. npm install
  66. npm run check # typecheck, unit tests (a failing fixture for every case check), plugin validation; runs in CI
  67. npm run agent -- --gateway /abs/path/trialrun-mcp/dist/server.js # live agent runs (manual; needs Claude Code)
  68. npm run agent -- --gateway /abs/path/trialrun-mcp/dist/server.js --builtin-readers # readers enabled: does it still use the gateway?
  69. npm run agent -- --no-gateway # coach mode without the gateway
  70. ```
  71. | Path | What it holds |
  72. |---|---|
  73. | `plugins/trialrun/skills/trialrun/` | The skill: `SKILL.md` and `references/` |
  74. | `.claude-plugin/`, `plugins/trialrun/.claude-plugin/` | Marketplace and plugin manifests |
  75. | `evals/agent/` | Agent evaluation harness, cases, unit tests and results |
  76. | `scripts/` | Plugin and skill validation |
  77. ## Limitations
  78. - Coaching is judged by the model, so it can miss a moment or add one that isn't needed.
  79. - Answers to technical questions can be long.
  80. - Without the gateway, the skill sees only what's in the conversation.
  81. Part of TrialRun, built for Cambridge EduX 2026.
  82. ## Licence
  83. MIT

Ratings and comments

Sign in to rate this skill.

Sign in

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