CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

lab-inventory-predictor

Predict depletion time of critical lab reagents based on historical usage frequency, and automatically generate purchase alerts when stock falls below safety thresholds.

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Other/lab-inventory-predictor/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a well-structured, largely executable reference with real validation checkpoints and a genuine fallback path, held back by redundant boilerplate sections, a contradictory pip-install line, and a Python import path that does not match the bundle. It lands noticeably above the midpoint.

Suggestions

Fix the Python API example's import path to match the actual bundle (e.g., importing from scripts/main.py or documenting the real package layout).

Remove the 'pip install -r requirements.txt' block that contradicts 'No external dependencies' (no requirements.txt exists).

Merge the overlapping Workflow, Output Requirements, and Response Template sections into one concrete sequence of commands to cut abstract boilerplate.

Consider moving the per-action parameter tables and the response template into a references/ file so SKILL.md stays a lean overview.

DimensionReasoningScore

Conciseness

The parameter tables, CLI examples, and algorithm formulas are tight, but the body includes unnecessary or contradictory material: 'pip install -r requirements.txt' appears directly under 'No external dependencies' (no requirements.txt exists in the bundle), and the 'Workflow', 'Output Requirements', and 'Response Template' sections repeat the same abstract boilerplate ('Confirm the user objective, required inputs, and non-negotiable constraints'). This fits the 'mostly efficient but includes some unnecessary explanation' anchor rather than the minor-trim level of 4.

3 / 5

Actionability

Concrete, executable CLI commands with realistic flags, complete parameter tables, explicit algorithm formulas, and a Python API example whose InventoryPredictor class genuinely exists in scripts/main.py. It falls short of fully copy-paste ready because the Python snippet's import path 'from skills.lab_inventory_predictor import InventoryPredictor' does not match the actual bundle layout (scripts/main.py), so it would not run as written.

4 / 5

Workflow Clarity

Validation checkpoints are explicit and up front ('python -m py_compile scripts/main.py', '--help', '--action status' in Quick Check), with a Fallback Behavior section that reports exact failure points and re-runs a status check, and LOW_CONFIDENCE flagging for sparse data. It is not a 5 because the numbered Workflow steps themselves are abstract directives ('Confirm the user objective...', 'Return a structured result...') rather than a concrete operational sequence of commands.

4 / 5

Progressive Disclosure

The single bundle file (scripts/main.py) is real and correctly referenced, sections are clearly headed and easy to navigate, and there are no nested or dangling references. It is a 4 rather than 5 because at roughly 200 lines everything is inlined in SKILL.md — the parameter tables, response template, and algorithm details could be split into reference files to keep the overview leaner.

4 / 5

Total

15

/

20

Passed

Description

53%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description states a clear, specific 'what' with two concrete actions in a distinct lab-reagent niche, but provides no explicit 'when to use' trigger clause and lacks natural synonyms like 'inventory' or 'reorder' that users would actually say. It sits just above the midpoint of the scale.

Suggestions

Append a trigger clause such as 'Use when the user mentions lab inventory, reagent stock running low, reorder timing, or when a reagent will run out.'

Include natural synonyms users would say — 'inventory', 'reorder', 'running low', 'stock levels' — to broaden trigger coverage.

Mention the additional documented capabilities (usage tracking, text/JSON/CSV reports, safety-stock alerts) to improve coverage without padding.

DimensionReasoningScore

Specificity

Names the lab reagent domain with exactly two concrete actions — 'Predict depletion time of critical lab reagents based on historical usage frequency' and 'automatically generate purchase alerts when stock falls below safety thresholds' — which matches the anchor for 1-2 concrete actions without comprehensive coverage. It is not a 4 because the body documents further capabilities (inventory tracking, report generation, safety-stock alerts) that the description omits.

3 / 5

Completeness

The 'what' is clearly and explicitly stated (depletion prediction and purchase alerts), but there is no 'Use when...' clause or equivalent explicit trigger guidance, capping completeness at 3 per the judging guidelines. It is not a 2 because the 'what' is concrete rather than vague.

3 / 5

Trigger Term Quality

Relevant keywords are present ('lab reagents', 'depletion', 'purchase alerts', 'stock', 'safety thresholds') but common natural variations users would say are missing, such as 'inventory', 'reorder', 'running low', or 'when will a reagent run out'. This fits the anchor for some relevant keywords with missing variations and synonyms, not the good coverage of a 4.

3 / 5

Distinctiveness Conflict Risk

The lab-reagent depletion-prediction niche is mostly distinct with clear triggers, carrying only minor overlap risk with generic inventory-management or shopping-list skills. It is not a 5 because terms like 'stock' and 'purchase alerts' alone could collide with broader inventory tooling if the lab-reagent context were dropped.

4 / 5

Total

13

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

aipoch/medical-research-skills

Path

scientific-skills/Other/lab-inventory-predictor/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.