CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

firebase

You're a developer who has shipped dozens of Firebase projects. You've seen the "easy" path lead to security breaches, runaway costs, and impossible migrations. You know Firebase is powerful, but you also know its sharp edges.

Quality

45%

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 ./plugins/AI-Agents-Safe-Coding-Skills/skills/firebase/SKILL.md

The canonical home for this skill is firebase in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

33%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-sectioned but nearly contentless skeleton: it enumerates capabilities, patterns, and anti-patterns as labels without any code, commands, explanations, or sequencing that would let Claude act on them. Its main defects are an incomplete/truncated persona narrative, unactionable one-line patterns, and a boilerplate 'When to Use' section. The strongest dimension is structure/organization; the weakest are workflow clarity and actionability.

Suggestions

Add executable examples to each pattern — e.g. a modular v9 SDK import snippet, a sample Firestore security rules block, and a data-modeling example showing a query-shaped collection — so the guidance is copy-paste usable.

Expand each anti-pattern with the failure mode and the fix (e.g. "❌ Listener on large collections: unbounded reads inflate cost — use queries with limits or pagination") instead of bare headings.

Repair the truncated sentence ("You advocate for Firebase w") and replace the filler 'When to Use' section with real trigger conditions; give Patterns/Anti-Patterns an ordered, validate-as-you-go sequence (e.g. design security rules first, verify with the Emulator Suite before deploy).

DimensionReasoningScore

Conciseness

The body is short and avoids explaining concepts Claude already knows, but the opening persona paragraph duplicates the frontmatter description verbatim, ends in a truncated sentence ("You advocate for Firebase w"), and "When to Use" is generic filler ("applicable to execute the workflow or actions described in the overview") — unnecessary tokens that could be trimmed, matching anchor 3. Not anchor 4: more than minor instances of removable content.

3 / 5

Actionability

No code, commands, or executable guidance anywhere: patterns are one-line hints ("Import only what you need for smaller bundles" without showing modular imports) and anti-patterns are bare headings ("❌ No Security Rules") with no explanation or fix, matching anchor 2 (high-level hints missing specific steps). Not anchor 1: the capability and pattern/anti-pattern lists do provide minimal directional guidance, more than a single vague instruction.

2 / 5

Workflow Clarity

No sequence, steps, or process is present at all — the sections are topic lists, not a workflow, and the simple-skill exception does not apply because there is no unambiguous single action to perform, matching anchor 1 ('steps missing or incoherent; no sequence'). Not anchor 2: even a rough sequence is absent.

1 / 5

Progressive Disclosure

At ~40 lines with no bundle files (references/scripts/assets do not exist) and clear section headers (Capabilities, Patterns, Anti-Patterns, Related Skills), the structure is appropriate for a short skill, matching anchor 4. Not 5: the truncated line, the filler 'When to Use' section, and 'Related Skills' pointing at skill names that exist neither in the bundle nor as resolvable files are minor organization gaps.

4 / 5

Total

10

/

20

Passed

Description

31%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 is a second-person persona narrative rather than a capability description: it conveys attitude and experience but never states what the skill does or when to invoke it. It relies on the single keyword "Firebase" for triggering and would benefit from a full rewrite in third person with explicit actions and a 'Use when...' clause.

Suggestions

Rewrite in third person stating concrete actions, e.g. "Designs Firestore data models, writes Firebase security rules, configures Auth, and sets up Cloud Functions, prioritizing security and cost control."

Add an explicit trigger clause: "Use when building, reviewing, or debugging Firebase projects, including Firestore, Firebase Auth, Cloud Functions, Storage, or security rules."

Include natural product-level synonyms users actually say (Firestore, Firebase Auth, security rules, emulators) so it triggers on the component being discussed, not just the word Firebase.

DimensionReasoningScore

Specificity

The description names the domain (Firebase) but states zero actions the skill performs — it is persona framing ("You're a developer who has shipped dozens of Firebase projects"), not capability description, matching anchor 2 before applying the rubric's mandatory 1-point penalty for second-person voice ("You're a developer"), yielding 1. It is not pure abstract language with no domain (anchor 1's precondition), but no concrete action survives the penalty, confirming 1 over 2.

1 / 5

Completeness

There is no explicit 'when' guidance at all (capped at 3 by the rubric), and the 'what' is only a vague implied expertise — the description never says what the skill does (advise, build, review), matching anchor 2 ('has a vague what and no when'). Not anchor 3, which requires a clear 'what'.

2 / 5

Trigger Term Quality

"Firebase" (repeated) is a genuine natural keyword, and "security breaches, runaway costs, ... migrations" add topical terms, but common variations users would say — Firestore, Firebase Auth, security rules, "Use when building with Firebase" — are missing, matching anchor 3. Not anchor 4: keyword coverage is one product name plus scenario words, not good broad coverage.

3 / 5

Distinctiveness Conflict Risk

Firebase-specific naming keeps it above generic (anchors 1–2), but with no explicit trigger guidance and no niche defined within Firebase, it would overlap with any Firebase-adjacent skill (hosting, auth-only, Firestore-only skills), matching anchor 3. Not anchor 4: it lacks the distinct concrete triggers that would bound the overlap.

3 / 5

Total

9

/

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

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

plugins/AI-Agents-Safe-Coding-Skills/skills/firebase/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.